github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10140] ollama version 5.11.0 is too slow in the generate process #6654

New Issue
Closed
opened 2026-04-12 18:20:53 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-12 18:20:53 -05:00
Owner
Copy Link

Originally created by @bravelyi on GitHub (Apr 5, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10140

2025/04/06 00:02:02 routes.go:1186: INFO server config env="map[CUDA_VISIBLE_DEVICES:0 GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/chenjy/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-04-06T00:02:02.319+08:00 level=INFO source=images.go:432 msg="total blobs: 84"
time=2025-04-06T00:02:02.320+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-04-06T00:02:02.321+08:00 level=INFO source=routes.go:1237 msg="Listening on [::]:11434 (version 0.5.11)"
time=2025-04-06T00:02:02.321+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-04-06T00:02:02.525+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-f075a0d8-8661-5d06-400f-0490085b57ad library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA L20" total="44.5 GiB" available="43.9 GiB"
time=2025-04-06T00:03:45.543+08:00 level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 gpu=GPU-f075a0d8-8661-5d06-400f-0490085b57ad parallel=4 available=47179563008 required="6.5 GiB"
time=2025-04-06T00:03:45.672+08:00 level=INFO source=server.go:100 msg="system memory" total="125.5 GiB" free="100.1 GiB" free_swap="959.8 MiB"
time=2025-04-06T00:03:45.673+08:00 level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[43.9 GiB]" memory.gpu_overhead="0 B" memory.required.full="6.5 GiB" memory.required.partial="6.5 GiB" memory.required.kv="1.0 GiB" memory.required.allocations="[6.5 GiB]" memory.weights.total="4.9 GiB" memory.weights.repeating="4.5 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="677.5 MiB"
time=2025-04-06T00:03:45.674+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 --ctx-size 8192 --batch-size 512 --n-gpu-layers 33 --threads 32 --parallel 4 --port 42285"
time=2025-04-06T00:03:45.677+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2025-04-06T00:03:45.677+08:00 level=INFO source=server.go:557 msg="waiting for llama runner to start responding"
time=2025-04-06T00:03:45.678+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error"
time=2025-04-06T00:03:45.704+08:00 level=INFO source=runner.go:936 msg="starting go runner"
time=2025-04-06T00:03:45.704+08:00 level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(gcc)" threads=32
time=2025-04-06T00:03:45.707+08:00 level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:42285"
llama_model_loader: loaded meta data with 29 key-value pairs and 292 tensors from /home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Meta Llama 3.1 8B Instruct
llama_model_loader: - kv 3: general.finetune str = Instruct
llama_model_loader: - kv 4: general.basename str = Meta-Llama-3.1
llama_model_loader: - kv 5: general.size_label str = 8B
llama_model_loader: - kv 6: general.license str = llama3.1
llama_model_loader: - kv 7: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam...
llama_model_loader: - kv 8: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ...
llama_model_loader: - kv 9: llama.block_count u32 = 32
llama_model_loader: - kv 10: llama.context_length u32 = 131072
llama_model_loader: - kv 11: llama.embedding_length u32 = 4096
llama_model_loader: - kv 12: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 13: llama.attention.head_count u32 = 32
llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000
llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 17: general.file_type u32 = 15
llama_model_loader: - kv 18: llama.vocab_size u32 = 128256
llama_model_loader: - kv 19: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 20: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 21: tokenizer.ggml.pre str = llama-bpe
llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,128256] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 24: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv 25: tokenizer.ggml.bos_token_id u32 = 128000
llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 128009
llama_model_loader: - kv 27: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ...
llama_model_loader: - kv 28: general.quantization_version u32 = 2
llama_model_loader: - type f32: 66 tensors
llama_model_loader: - type q4_K: 193 tensors
llama_model_loader: - type q6_K: 33 tensors
time=2025-04-06T00:03:45.930+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model"
llm_load_vocab: special tokens cache size = 256
llm_load_vocab: token to piece cache size = 0.7999 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = BPE
llm_load_print_meta: n_vocab = 128256
llm_load_print_meta: n_merges = 280147
llm_load_print_meta: vocab_only = 0
llm_load_print_meta: n_ctx_train = 131072
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 8
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_swa = 0
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 4
llm_load_print_meta: n_embd_k_gqa = 1024
llm_load_print_meta: n_embd_v_gqa = 1024
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale = 0.0e+00
llm_load_print_meta: n_ff = 14336
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: causal attn = 1
llm_load_print_meta: pooling type = 0
llm_load_print_meta: rope type = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 500000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn = 131072
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: ssm_d_conv = 0
llm_load_print_meta: ssm_d_inner = 0
llm_load_print_meta: ssm_d_state = 0
llm_load_print_meta: ssm_dt_rank = 0
llm_load_print_meta: ssm_dt_b_c_rms = 0
llm_load_print_meta: model type = 8B
llm_load_print_meta: model ftype = Q4_K - Medium
llm_load_print_meta: model params = 8.03 B
llm_load_print_meta: model size = 4.58 GiB (4.89 BPW)
llm_load_print_meta: general.name = Meta Llama 3.1 8B Instruct
llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token = 128009 '<|eot_id|>'
llm_load_print_meta: EOT token = 128009 '<|eot_id|>'
llm_load_print_meta: EOM token = 128008 '<|eom_id|>'
llm_load_print_meta: LF token = 128 'Ä'
llm_load_print_meta: EOG token = 128008 '<|eom_id|>'
llm_load_print_meta: EOG token = 128009 '<|eot_id|>'
llm_load_print_meta: max token length = 256
llm_load_tensors: CPU_Mapped model buffer size = 4685.30 MiB
llama_new_context_with_model: n_seq_max = 4
llama_new_context_with_model: n_ctx = 8192
llama_new_context_with_model: n_ctx_per_seq = 2048
llama_new_context_with_model: n_batch = 2048
llama_new_context_with_model: n_ubatch = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base = 500000.0
llama_new_context_with_model: freq_scale = 1
llama_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
llama_kv_cache_init: kv_size = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1
llama_kv_cache_init: CPU KV buffer size = 1024.00 MiB
llama_new_context_with_model: KV self size = 1024.00 MiB, K (f16): 512.00 MiB, V (f16): 512.00 MiB
llama_new_context_with_model: CPU output buffer size = 2.02 MiB
llama_new_context_with_model: CPU compute buffer size = 560.01 MiB
llama_new_context_with_model: graph nodes = 1030
llama_new_context_with_model: graph splits = 1
time=2025-04-06T00:03:47.486+08:00 level=INFO source=server.go:596 msg="llama runner started in 1.81 seconds"
[GIN] 2025/04/06 - 00:06:08 | 200 | 107.184µs | 127.0.0.1 | HEAD "/"
[GIN] 2025/04/06 - 00:06:08 | 200 | 47.115901ms | 127.0.0.1 | POST "/api/show"
time=2025-04-06T00:06:08.546+08:00 level=INFO source=sched.go:507 msg="updated VRAM based on existing loaded models" gpu=GPU-f075a0d8-8661-5d06-400f-0490085b57ad library=cuda total="44.5 GiB" available="38.1 GiB"
time=2025-04-06T00:06:08.547+08:00 level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/home/chenjy/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa gpu=GPU-f075a0d8-8661-5d06-400f-0490085b57ad parallel=4 available=40873564160 required="6.2 GiB"
time=2025-04-06T00:06:08.704+08:00 level=INFO source=server.go:100 msg="system memory" total="125.5 GiB" free="98.0 GiB" free_swap="959.6 MiB"
time=2025-04-06T00:06:08.705+08:00 level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[38.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="6.2 GiB" memory.required.partial="6.2 GiB" memory.required.kv="1.0 GiB" memory.required.allocations="[6.2 GiB]" memory.weights.total="4.7 GiB" memory.weights.repeating="4.3 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="677.5 MiB"
time=2025-04-06T00:06:08.705+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /home/chenjy/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa --ctx-size 8192 --batch-size 512 --n-gpu-layers 33 --threads 32 --parallel 4 --port 40167"
time=2025-04-06T00:06:08.710+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=2
time=2025-04-06T00:06:08.710+08:00 level=INFO source=server.go:557 msg="waiting for llama runner to start responding"
time=2025-04-06T00:06:08.711+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error"
time=2025-04-06T00:06:08.743+08:00 level=INFO source=runner.go:936 msg="starting go runner"
time=2025-04-06T00:06:08.744+08:00 level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(gcc)" threads=32
time=2025-04-06T00:06:08.744+08:00 level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:40167"
llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from /home/chenjy/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.name str = Meta-Llama-3-8B-Instruct
llama_model_loader: - kv 2: llama.block_count u32 = 32
llama_model_loader: - kv 3: llama.context_length u32 = 8192
llama_model_loader: - kv 4: llama.embedding_length u32 = 4096
llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 6: llama.attention.head_count u32 = 32
llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 8: llama.rope.freq_base f32 = 500000.000000
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 10: general.file_type u32 = 2
llama_model_loader: - kv 11: llama.vocab_size u32 = 128256
llama_model_loader: - kv 12: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 13: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 14: tokenizer.ggml.pre str = llama-bpe
llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,128256] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 17: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 128000
llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 128009
llama_model_loader: - kv 20: tokenizer.chat_template str = {% set loop_messages = messages %}{% ...
llama_model_loader: - kv 21: general.quantization_version u32 = 2
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q4_0: 225 tensors
llama_model_loader: - type q6_K: 1 tensors
time=2025-04-06T00:06:08.963+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model"
llm_load_vocab: special tokens cache size = 256
llm_load_vocab: token to piece cache size = 0.8000 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = BPE
llm_load_print_meta: n_vocab = 128256
llm_load_print_meta: n_merges = 280147
llm_load_print_meta: vocab_only = 0
llm_load_print_meta: n_ctx_train = 8192
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 8
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_swa = 0
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 4
llm_load_print_meta: n_embd_k_gqa = 1024
llm_load_print_meta: n_embd_v_gqa = 1024
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale = 0.0e+00
llm_load_print_meta: n_ff = 14336
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: causal attn = 1
llm_load_print_meta: pooling type = 0
llm_load_print_meta: rope type = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 500000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn = 8192
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: ssm_d_conv = 0
llm_load_print_meta: ssm_d_inner = 0
llm_load_print_meta: ssm_d_state = 0
llm_load_print_meta: ssm_dt_rank = 0
llm_load_print_meta: ssm_dt_b_c_rms = 0
llm_load_print_meta: model type = 8B
llm_load_print_meta: model ftype = Q4_0
llm_load_print_meta: model params = 8.03 B
llm_load_print_meta: model size = 4.33 GiB (4.64 BPW)
llm_load_print_meta: general.name = Meta-Llama-3-8B-Instruct
llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token = 128009 '<|eot_id|>'
llm_load_print_meta: EOT token = 128009 '<|eot_id|>'
llm_load_print_meta: LF token = 128 'Ä'
llm_load_print_meta: EOG token = 128009 '<|eot_id|>'
llm_load_print_meta: max token length = 256
llm_load_tensors: CPU_Mapped model buffer size = 4437.80 MiB
llama_new_context_with_model: n_seq_max = 4
llama_new_context_with_model: n_ctx = 8192
llama_new_context_with_model: n_ctx_per_seq = 2048
llama_new_context_with_model: n_batch = 2048
llama_new_context_with_model: n_ubatch = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base = 500000.0
llama_new_context_with_model: freq_scale = 1
llama_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (8192) -- the full capacity of the model will not be utilized
llama_kv_cache_init: kv_size = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1
llama_kv_cache_init: CPU KV buffer size = 1024.00 MiB
llama_new_context_with_model: KV self size = 1024.00 MiB, K (f16): 512.00 MiB, V (f16): 512.00 MiB
llama_new_context_with_model: CPU output buffer size = 2.02 MiB
llama_new_context_with_model: CPU compute buffer size = 560.01 MiB
llama_new_context_with_model: graph nodes = 1030
llama_new_context_with_model: graph splits = 1
time=2025-04-06T00:06:10.973+08:00 level=INFO source=server.go:596 msg="llama runner started in 2.26 seconds"
[GIN] 2025/04/06 - 00:06:10 | 200 | 2.680203419s | 127.0.0.1 | POST "/api/generate"
[GIN] 2025/04/06 - 00:14:32 | 200 | 8m19s | 127.0.0.1 | POST "/api/chat"
[GIN] 2025/04/06 - 00:14:37 | 200 | 30.541µs | 127.0.0.1 | HEAD "/"
[GIN] 2025/04/06 - 00:14:37 | 200 | 1.628466ms | 127.0.0.1 | GET "/api/tags"
llama_model_loader: loaded meta data with 29 key-value pairs and 292 tensors from /home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Meta Llama 3.1 8B Instruct
llama_model_loader: - kv 3: general.finetune str = Instruct
llama_model_loader: - kv 4: general.basename str = Meta-Llama-3.1
llama_model_loader: - kv 5: general.size_label str = 8B
llama_model_loader: - kv 6: general.license str = llama3.1
llama_model_loader: - kv 7: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam...
llama_model_loader: - kv 8: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ...
llama_model_loader: - kv 9: llama.block_count u32 = 32
llama_model_loader: - kv 10: llama.context_length u32 = 131072
llama_model_loader: - kv 11: llama.embedding_length u32 = 4096
llama_model_loader: - kv 12: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 13: llama.attention.head_count u32 = 32
llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000
llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 17: general.file_type u32 = 15
llama_model_loader: - kv 18: llama.vocab_size u32 = 128256
llama_model_loader: - kv 19: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 20: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 21: tokenizer.ggml.pre str = llama-bpe
llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,128256] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 24: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv 25: tokenizer.ggml.bos_token_id u32 = 128000
llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 128009
llama_model_loader: - kv 27: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ...
llama_model_loader: - kv 28: general.quantization_version u32 = 2
llama_model_loader: - type f32: 66 tensors
llama_model_loader: - type q4_K: 193 tensors
llama_model_loader: - type q6_K: 33 tensors
llm_load_vocab: special tokens cache size = 256
llm_load_vocab: token to piece cache size = 0.7999 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = BPE
llm_load_print_meta: n_vocab = 128256
llm_load_print_meta: n_merges = 280147
llm_load_print_meta: vocab_only = 1
llm_load_print_meta: model type = ?B
llm_load_print_meta: model ftype = all F32
llm_load_print_meta: model params = 8.03 B
llm_load_print_meta: model size = 4.58 GiB (4.89 BPW)
llm_load_print_meta: general.name = Meta Llama 3.1 8B Instruct
llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token = 128009 '<|eot_id|>'
llm_load_print_meta: EOT token = 128009 '<|eot_id|>'
llm_load_print_meta: EOM token = 128008 '<|eom_id|>'
llm_load_print_meta: LF token = 128 'Ä'
llm_load_print_meta: EOG token = 128008 '<|eom_id|>'
llm_load_print_meta: EOG token = 128009 '<|eot_id|>'
llm_load_print_meta: max token length = 256
llama_model_load: vocab only - skipping tensors
[GIN] 2025/04/06 - 00:14:50 | 200 | 11m5s | 127.0.0.1 | POST "/api/generate"
[GIN] 2025/04/06 - 00:15:06 | 200 | 11m21s | 127.0.0.1 | POST "/api/generate"
[GIN] 2025/04/06 - 00:15:13 | 200 | 11m28s | 127.0.0.1 | POST "/api/generate"
[GIN] 2025/04/06 - 00:16:19 | 200 | 12m34s | 127.0.0.1 | POST "/api/generate"
[GIN] 2025/04/06 - 00:17:51 | 200 | 13m13s | 127.0.0.1 | POST "/api/generate"
[GIN] 2025/04/06 - 00:19:02 | 200 | 14m23s | 127.0.0.1 | POST "/api/generate"

Originally created by @bravelyi on GitHub (Apr 5, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10140 2025/04/06 00:02:02 routes.go:1186: INFO server config env="map[CUDA_VISIBLE_DEVICES:0 GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/chenjy/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-04-06T00:02:02.319+08:00 level=INFO source=images.go:432 msg="total blobs: 84" time=2025-04-06T00:02:02.320+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-04-06T00:02:02.321+08:00 level=INFO source=routes.go:1237 msg="Listening on [::]:11434 (version 0.5.11)" time=2025-04-06T00:02:02.321+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-04-06T00:02:02.525+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-f075a0d8-8661-5d06-400f-0490085b57ad library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA L20" total="44.5 GiB" available="43.9 GiB" time=2025-04-06T00:03:45.543+08:00 level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 gpu=GPU-f075a0d8-8661-5d06-400f-0490085b57ad parallel=4 available=47179563008 required="6.5 GiB" time=2025-04-06T00:03:45.672+08:00 level=INFO source=server.go:100 msg="system memory" total="125.5 GiB" free="100.1 GiB" free_swap="959.8 MiB" time=2025-04-06T00:03:45.673+08:00 level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[43.9 GiB]" memory.gpu_overhead="0 B" memory.required.full="6.5 GiB" memory.required.partial="6.5 GiB" memory.required.kv="1.0 GiB" memory.required.allocations="[6.5 GiB]" memory.weights.total="4.9 GiB" memory.weights.repeating="4.5 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="677.5 MiB" time=2025-04-06T00:03:45.674+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 --ctx-size 8192 --batch-size 512 --n-gpu-layers 33 --threads 32 --parallel 4 --port 42285" time=2025-04-06T00:03:45.677+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2025-04-06T00:03:45.677+08:00 level=INFO source=server.go:557 msg="waiting for llama runner to start responding" time=2025-04-06T00:03:45.678+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error" time=2025-04-06T00:03:45.704+08:00 level=INFO source=runner.go:936 msg="starting go runner" time=2025-04-06T00:03:45.704+08:00 level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(gcc)" threads=32 time=2025-04-06T00:03:45.707+08:00 level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:42285" llama_model_loader: loaded meta data with 29 key-value pairs and 292 tensors from /home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Meta Llama 3.1 8B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Meta-Llama-3.1 llama_model_loader: - kv 5: general.size_label str = 8B llama_model_loader: - kv 6: general.license str = llama3.1 llama_model_loader: - kv 7: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam... llama_model_loader: - kv 8: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ... llama_model_loader: - kv 9: llama.block_count u32 = 32 llama_model_loader: - kv 10: llama.context_length u32 = 131072 llama_model_loader: - kv 11: llama.embedding_length u32 = 4096 llama_model_loader: - kv 12: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 13: llama.attention.head_count u32 = 32 llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 17: general.file_type u32 = 15 llama_model_loader: - kv 18: llama.vocab_size u32 = 128256 llama_model_loader: - kv 19: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 20: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 21: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 24: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 25: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 27: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ... llama_model_loader: - kv 28: general.quantization_version u32 = 2 llama_model_loader: - type f32: 66 tensors llama_model_loader: - type q4_K: 193 tensors llama_model_loader: - type q6_K: 33 tensors time=2025-04-06T00:03:45.930+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model" llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 0.7999 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 131072 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_layer = 32 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_swa = 0 llm_load_print_meta: n_embd_head_k = 128 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 4 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 14336 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: causal attn = 1 llm_load_print_meta: pooling type = 0 llm_load_print_meta: rope type = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 500000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 131072 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: ssm_d_conv = 0 llm_load_print_meta: ssm_d_inner = 0 llm_load_print_meta: ssm_d_state = 0 llm_load_print_meta: ssm_dt_rank = 0 llm_load_print_meta: ssm_dt_b_c_rms = 0 llm_load_print_meta: model type = 8B llm_load_print_meta: model ftype = Q4_K - Medium llm_load_print_meta: model params = 8.03 B llm_load_print_meta: model size = 4.58 GiB (4.89 BPW) llm_load_print_meta: general.name = Meta Llama 3.1 8B Instruct llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128009 '<|eot_id|>' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_print_meta: EOM token = 128008 '<|eom_id|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOG token = 128008 '<|eom_id|>' llm_load_print_meta: EOG token = 128009 '<|eot_id|>' llm_load_print_meta: max token length = 256 llm_load_tensors: CPU_Mapped model buffer size = 4685.30 MiB llama_new_context_with_model: n_seq_max = 4 llama_new_context_with_model: n_ctx = 8192 llama_new_context_with_model: n_ctx_per_seq = 2048 llama_new_context_with_model: n_batch = 2048 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 500000.0 llama_new_context_with_model: freq_scale = 1 llama_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (131072) -- the full capacity of the model will not be utilized llama_kv_cache_init: kv_size = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1 llama_kv_cache_init: CPU KV buffer size = 1024.00 MiB llama_new_context_with_model: KV self size = 1024.00 MiB, K (f16): 512.00 MiB, V (f16): 512.00 MiB llama_new_context_with_model: CPU output buffer size = 2.02 MiB llama_new_context_with_model: CPU compute buffer size = 560.01 MiB llama_new_context_with_model: graph nodes = 1030 llama_new_context_with_model: graph splits = 1 time=2025-04-06T00:03:47.486+08:00 level=INFO source=server.go:596 msg="llama runner started in 1.81 seconds" [GIN] 2025/04/06 - 00:06:08 | 200 | 107.184µs | 127.0.0.1 | HEAD "/" [GIN] 2025/04/06 - 00:06:08 | 200 | 47.115901ms | 127.0.0.1 | POST "/api/show" time=2025-04-06T00:06:08.546+08:00 level=INFO source=sched.go:507 msg="updated VRAM based on existing loaded models" gpu=GPU-f075a0d8-8661-5d06-400f-0490085b57ad library=cuda total="44.5 GiB" available="38.1 GiB" time=2025-04-06T00:06:08.547+08:00 level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/home/chenjy/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa gpu=GPU-f075a0d8-8661-5d06-400f-0490085b57ad parallel=4 available=40873564160 required="6.2 GiB" time=2025-04-06T00:06:08.704+08:00 level=INFO source=server.go:100 msg="system memory" total="125.5 GiB" free="98.0 GiB" free_swap="959.6 MiB" time=2025-04-06T00:06:08.705+08:00 level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[38.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="6.2 GiB" memory.required.partial="6.2 GiB" memory.required.kv="1.0 GiB" memory.required.allocations="[6.2 GiB]" memory.weights.total="4.7 GiB" memory.weights.repeating="4.3 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="677.5 MiB" time=2025-04-06T00:06:08.705+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /home/chenjy/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa --ctx-size 8192 --batch-size 512 --n-gpu-layers 33 --threads 32 --parallel 4 --port 40167" time=2025-04-06T00:06:08.710+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=2 time=2025-04-06T00:06:08.710+08:00 level=INFO source=server.go:557 msg="waiting for llama runner to start responding" time=2025-04-06T00:06:08.711+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error" time=2025-04-06T00:06:08.743+08:00 level=INFO source=runner.go:936 msg="starting go runner" time=2025-04-06T00:06:08.744+08:00 level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(gcc)" threads=32 time=2025-04-06T00:06:08.744+08:00 level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:40167" llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from /home/chenjy/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.name str = Meta-Llama-3-8B-Instruct llama_model_loader: - kv 2: llama.block_count u32 = 32 llama_model_loader: - kv 3: llama.context_length u32 = 8192 llama_model_loader: - kv 4: llama.embedding_length u32 = 4096 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: llama.attention.head_count u32 = 32 llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 8: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 10: general.file_type u32 = 2 llama_model_loader: - kv 11: llama.vocab_size u32 = 128256 llama_model_loader: - kv 12: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 13: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 14: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 17: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 20: tokenizer.chat_template str = {% set loop_messages = messages %}{% ... llama_model_loader: - kv 21: general.quantization_version u32 = 2 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q4_0: 225 tensors llama_model_loader: - type q6_K: 1 tensors time=2025-04-06T00:06:08.963+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model" llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 0.8000 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 8192 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_layer = 32 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_swa = 0 llm_load_print_meta: n_embd_head_k = 128 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 4 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 14336 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: causal attn = 1 llm_load_print_meta: pooling type = 0 llm_load_print_meta: rope type = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 500000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 8192 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: ssm_d_conv = 0 llm_load_print_meta: ssm_d_inner = 0 llm_load_print_meta: ssm_d_state = 0 llm_load_print_meta: ssm_dt_rank = 0 llm_load_print_meta: ssm_dt_b_c_rms = 0 llm_load_print_meta: model type = 8B llm_load_print_meta: model ftype = Q4_0 llm_load_print_meta: model params = 8.03 B llm_load_print_meta: model size = 4.33 GiB (4.64 BPW) llm_load_print_meta: general.name = Meta-Llama-3-8B-Instruct llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128009 '<|eot_id|>' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOG token = 128009 '<|eot_id|>' llm_load_print_meta: max token length = 256 llm_load_tensors: CPU_Mapped model buffer size = 4437.80 MiB llama_new_context_with_model: n_seq_max = 4 llama_new_context_with_model: n_ctx = 8192 llama_new_context_with_model: n_ctx_per_seq = 2048 llama_new_context_with_model: n_batch = 2048 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 500000.0 llama_new_context_with_model: freq_scale = 1 llama_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (8192) -- the full capacity of the model will not be utilized llama_kv_cache_init: kv_size = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1 llama_kv_cache_init: CPU KV buffer size = 1024.00 MiB llama_new_context_with_model: KV self size = 1024.00 MiB, K (f16): 512.00 MiB, V (f16): 512.00 MiB llama_new_context_with_model: CPU output buffer size = 2.02 MiB llama_new_context_with_model: CPU compute buffer size = 560.01 MiB llama_new_context_with_model: graph nodes = 1030 llama_new_context_with_model: graph splits = 1 time=2025-04-06T00:06:10.973+08:00 level=INFO source=server.go:596 msg="llama runner started in 2.26 seconds" [GIN] 2025/04/06 - 00:06:10 | 200 | 2.680203419s | 127.0.0.1 | POST "/api/generate" [GIN] 2025/04/06 - 00:14:32 | 200 | 8m19s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/04/06 - 00:14:37 | 200 | 30.541µs | 127.0.0.1 | HEAD "/" [GIN] 2025/04/06 - 00:14:37 | 200 | 1.628466ms | 127.0.0.1 | GET "/api/tags" llama_model_loader: loaded meta data with 29 key-value pairs and 292 tensors from /home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Meta Llama 3.1 8B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Meta-Llama-3.1 llama_model_loader: - kv 5: general.size_label str = 8B llama_model_loader: - kv 6: general.license str = llama3.1 llama_model_loader: - kv 7: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam... llama_model_loader: - kv 8: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ... llama_model_loader: - kv 9: llama.block_count u32 = 32 llama_model_loader: - kv 10: llama.context_length u32 = 131072 llama_model_loader: - kv 11: llama.embedding_length u32 = 4096 llama_model_loader: - kv 12: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 13: llama.attention.head_count u32 = 32 llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 17: general.file_type u32 = 15 llama_model_loader: - kv 18: llama.vocab_size u32 = 128256 llama_model_loader: - kv 19: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 20: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 21: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 24: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 25: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 27: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ... llama_model_loader: - kv 28: general.quantization_version u32 = 2 llama_model_loader: - type f32: 66 tensors llama_model_loader: - type q4_K: 193 tensors llama_model_loader: - type q6_K: 33 tensors llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 0.7999 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: vocab_only = 1 llm_load_print_meta: model type = ?B llm_load_print_meta: model ftype = all F32 llm_load_print_meta: model params = 8.03 B llm_load_print_meta: model size = 4.58 GiB (4.89 BPW) llm_load_print_meta: general.name = Meta Llama 3.1 8B Instruct llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128009 '<|eot_id|>' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_print_meta: EOM token = 128008 '<|eom_id|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOG token = 128008 '<|eom_id|>' llm_load_print_meta: EOG token = 128009 '<|eot_id|>' llm_load_print_meta: max token length = 256 llama_model_load: vocab only - skipping tensors [GIN] 2025/04/06 - 00:14:50 | 200 | 11m5s | 127.0.0.1 | POST "/api/generate" [GIN] 2025/04/06 - 00:15:06 | 200 | 11m21s | 127.0.0.1 | POST "/api/generate" [GIN] 2025/04/06 - 00:15:13 | 200 | 11m28s | 127.0.0.1 | POST "/api/generate" [GIN] 2025/04/06 - 00:16:19 | 200 | 12m34s | 127.0.0.1 | POST "/api/generate" [GIN] 2025/04/06 - 00:17:51 | 200 | 13m13s | 127.0.0.1 | POST "/api/generate" [GIN] 2025/04/06 - 00:19:02 | 200 | 14m23s | 127.0.0.1 | POST "/api/generate"
GiteaMirror added the model label 2026-04-12 18:20:53 -05:00
GiteaMirror commented 2026-04-12 18:20:55 -05:00
Author
Owner
Copy Link

@bravelyi commented on GitHub (Apr 5, 2025):

But in v3.14.0 it's very fast, 1s a response.

<!-- gh-comment-id:2780963274 --> @bravelyi commented on GitHub (Apr 5, 2025): But in v3.14.0 it's very fast, 1s a response.
GiteaMirror commented 2026-04-12 18:20:56 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Apr 5, 2025):

You mean 0llama version 0.5.11 and version 0.3.14
could you try with version 0.6.4?

<!-- gh-comment-id:2780964139 --> @igorschlum commented on GitHub (Apr 5, 2025): You mean 0llama version 0.5.11 and version 0.3.14 could you try with version 0.6.4?
GiteaMirror commented 2026-04-12 18:20:57 -05:00
Author
Owner
Copy Link

@bravelyi commented on GitHub (Apr 5, 2025):

I tried 0.6.3 and it does the same thing, but my disk space is already 95%, does this have anything to do with the slow call speed, thanks!

<!-- gh-comment-id:2780976403 --> @bravelyi commented on GitHub (Apr 5, 2025): I tried 0.6.3 and it does the same thing, but my disk space is already 95%, does this have anything to do with the slow call speed, thanks!
GiteaMirror commented 2026-04-12 18:20:57 -05:00
Author
Owner
Copy Link

@bravelyi commented on GitHub (Apr 5, 2025):

2025/04/06 01:46:52 routes.go:1231: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:2048 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/chenjy/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-04-06T01:46:52.614+08:00 level=INFO source=images.go:458 msg="total blobs: 98"
time=2025-04-06T01:46:52.615+08:00 level=INFO source=images.go:465 msg="total unused blobs removed: 0"
time=2025-04-06T01:46:52.615+08:00 level=INFO source=routes.go:1298 msg="Listening on 127.0.0.1:11434 (version 0.6.4)"
time=2025-04-06T01:46:52.615+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-04-06T01:46:53.206+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-f075a0d8-8661-5d06-400f-0490085b57ad library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA L20" total="44.5 GiB" available="43.9 GiB"
time=2025-04-06T01:46:53.207+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-e27fa16c-0842-a43b-8014-d0a78556739a library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA L20" total="44.5 GiB" available="44.2 GiB"
time=2025-04-06T01:46:53.207+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-fe74533b-efbc-ddc9-e0ac-3768e837bc60 library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA L20" total="44.5 GiB" available="11.7 GiB"
time=2025-04-06T01:46:53.207+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-1cc534f8-b355-b585-210f-44fa8cc4e765 library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA L20" total="44.5 GiB" available="44.2 GiB"
time=2025-04-06T01:46:57.953+08:00 level=WARN source=ggml.go:149 msg="key not found" key=llama.vision.block_count default=0
time=2025-04-06T01:46:57.954+08:00 level=WARN source=ggml.go:149 msg="key not found" key=llama.attention.key_length default=128
time=2025-04-06T01:46:57.954+08:00 level=WARN source=ggml.go:149 msg="key not found" key=llama.attention.value_length default=128
time=2025-04-06T01:46:57.954+08:00 level=INFO source=sched.go:716 msg="new model will fit in available VRAM in single GPU, loading" model=/home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 gpu=GPU-1cc534f8-b355-b585-210f-44fa8cc4e765 parallel=4 available=47489810432 required="6.5 GiB"
time=2025-04-06T01:46:58.440+08:00 level=INFO source=server.go:105 msg="system memory" total="125.5 GiB" free="104.5 GiB" free_swap="840.6 MiB"
time=2025-04-06T01:46:58.440+08:00 level=WARN source=ggml.go:149 msg="key not found" key=llama.vision.block_count default=0
time=2025-04-06T01:46:58.440+08:00 level=WARN source=ggml.go:149 msg="key not found" key=llama.attention.key_length default=128
time=2025-04-06T01:46:58.440+08:00 level=WARN source=ggml.go:149 msg="key not found" key=llama.attention.value_length default=128
time=2025-04-06T01:46:58.441+08:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[44.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="6.5 GiB" memory.required.partial="6.5 GiB" memory.required.kv="1.0 GiB" memory.required.allocations="[6.5 GiB]" memory.weights.total="4.3 GiB" memory.weights.repeating="3.9 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="677.5 MiB"
llama_model_loader: loaded meta data with 29 key-value pairs and 292 tensors from /home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Meta Llama 3.1 8B Instruct
llama_model_loader: - kv 3: general.finetune str = Instruct
llama_model_loader: - kv 4: general.basename str = Meta-Llama-3.1
llama_model_loader: - kv 5: general.size_label str = 8B
llama_model_loader: - kv 6: general.license str = llama3.1
llama_model_loader: - kv 7: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam...
llama_model_loader: - kv 8: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ...
llama_model_loader: - kv 9: llama.block_count u32 = 32
llama_model_loader: - kv 10: llama.context_length u32 = 131072
llama_model_loader: - kv 11: llama.embedding_length u32 = 4096
llama_model_loader: - kv 12: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 13: llama.attention.head_count u32 = 32
llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000
llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 17: general.file_type u32 = 15
llama_model_loader: - kv 18: llama.vocab_size u32 = 128256
llama_model_loader: - kv 19: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 20: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 21: tokenizer.ggml.pre str = llama-bpe
llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,128256] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 24: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv 25: tokenizer.ggml.bos_token_id u32 = 128000
llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 128009
llama_model_loader: - kv 27: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ...
llama_model_loader: - kv 28: general.quantization_version u32 = 2
llama_model_loader: - type f32: 66 tensors
llama_model_loader: - type q4_K: 193 tensors
llama_model_loader: - type q6_K: 33 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 4.58 GiB (4.89 BPW)
load: special tokens cache size = 256
load: token to piece cache size = 0.7999 MB
print_info: arch = llama
print_info: vocab_only = 1
print_info: model type = ?B
print_info: model params = 8.03 B
print_info: general.name = Meta Llama 3.1 8B Instruct
print_info: vocab type = BPE
print_info: n_vocab = 128256
print_info: n_merges = 280147
print_info: BOS token = 128000 '<|begin_of_text|>'
print_info: EOS token = 128009 '<|eot_id|>'
print_info: EOT token = 128009 '<|eot_id|>'
print_info: EOM token = 128008 '<|eom_id|>'
print_info: LF token = 198 'Ċ'
print_info: EOG token = 128008 '<|eom_id|>'
print_info: EOG token = 128009 '<|eot_id|>'
print_info: max token length = 256
llama_model_load: vocab only - skipping tensors
time=2025-04-06T01:46:58.704+08:00 level=INFO source=server.go:405 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 --ctx-size 8192 --batch-size 512 --n-gpu-layers 33 --threads 32 --parallel 4 --port 35977"
time=2025-04-06T01:46:58.707+08:00 level=INFO source=sched.go:451 msg="loaded runners" count=1
time=2025-04-06T01:46:58.707+08:00 level=INFO source=server.go:580 msg="waiting for llama runner to start responding"
time=2025-04-06T01:46:58.707+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error"
time=2025-04-06T01:46:58.725+08:00 level=INFO source=runner.go:858 msg="starting go runner"
time=2025-04-06T01:46:58.725+08:00 level=INFO source=ggml.go:109 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)
time=2025-04-06T01:46:58.727+08:00 level=INFO source=runner.go:918 msg="Server listening on 127.0.0.1:35977"
llama_model_loader: loaded meta data with 29 key-value pairs and 292 tensors from /home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Meta Llama 3.1 8B Instruct
llama_model_loader: - kv 3: general.finetune str = Instruct
llama_model_loader: - kv 4: general.basename str = Meta-Llama-3.1
llama_model_loader: - kv 5: general.size_label str = 8B
llama_model_loader: - kv 6: general.license str = llama3.1
llama_model_loader: - kv 7: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam...
llama_model_loader: - kv 8: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ...
llama_model_loader: - kv 9: llama.block_count u32 = 32
llama_model_loader: - kv 10: llama.context_length u32 = 131072
llama_model_loader: - kv 11: llama.embedding_length u32 = 4096
llama_model_loader: - kv 12: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 13: llama.attention.head_count u32 = 32
llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000
llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 17: general.file_type u32 = 15
llama_model_loader: - kv 18: llama.vocab_size u32 = 128256
llama_model_loader: - kv 19: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 20: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 21: tokenizer.ggml.pre str = llama-bpe
llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,128256] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 24: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv 25: tokenizer.ggml.bos_token_id u32 = 128000
llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 128009
llama_model_loader: - kv 27: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ...
llama_model_loader: - kv 28: general.quantization_version u32 = 2
llama_model_loader: - type f32: 66 tensors
llama_model_loader: - type q4_K: 193 tensors
llama_model_loader: - type q6_K: 33 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 4.58 GiB (4.89 BPW)
load: special tokens cache size = 256
time=2025-04-06T01:46:58.961+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model"

Not a single response in five minutes.
The latest v0.6.4 version is also very slow, is there anyone who can tell me why?

<!-- gh-comment-id:2781016682 --> @bravelyi commented on GitHub (Apr 5, 2025): 2025/04/06 01:46:52 routes.go:1231: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:2048 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/chenjy/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-04-06T01:46:52.614+08:00 level=INFO source=images.go:458 msg="total blobs: 98" time=2025-04-06T01:46:52.615+08:00 level=INFO source=images.go:465 msg="total unused blobs removed: 0" time=2025-04-06T01:46:52.615+08:00 level=INFO source=routes.go:1298 msg="Listening on 127.0.0.1:11434 (version 0.6.4)" time=2025-04-06T01:46:52.615+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-04-06T01:46:53.206+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-f075a0d8-8661-5d06-400f-0490085b57ad library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA L20" total="44.5 GiB" available="43.9 GiB" time=2025-04-06T01:46:53.207+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-e27fa16c-0842-a43b-8014-d0a78556739a library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA L20" total="44.5 GiB" available="44.2 GiB" time=2025-04-06T01:46:53.207+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-fe74533b-efbc-ddc9-e0ac-3768e837bc60 library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA L20" total="44.5 GiB" available="11.7 GiB" time=2025-04-06T01:46:53.207+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-1cc534f8-b355-b585-210f-44fa8cc4e765 library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA L20" total="44.5 GiB" available="44.2 GiB" time=2025-04-06T01:46:57.953+08:00 level=WARN source=ggml.go:149 msg="key not found" key=llama.vision.block_count default=0 time=2025-04-06T01:46:57.954+08:00 level=WARN source=ggml.go:149 msg="key not found" key=llama.attention.key_length default=128 time=2025-04-06T01:46:57.954+08:00 level=WARN source=ggml.go:149 msg="key not found" key=llama.attention.value_length default=128 time=2025-04-06T01:46:57.954+08:00 level=INFO source=sched.go:716 msg="new model will fit in available VRAM in single GPU, loading" model=/home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 gpu=GPU-1cc534f8-b355-b585-210f-44fa8cc4e765 parallel=4 available=47489810432 required="6.5 GiB" time=2025-04-06T01:46:58.440+08:00 level=INFO source=server.go:105 msg="system memory" total="125.5 GiB" free="104.5 GiB" free_swap="840.6 MiB" time=2025-04-06T01:46:58.440+08:00 level=WARN source=ggml.go:149 msg="key not found" key=llama.vision.block_count default=0 time=2025-04-06T01:46:58.440+08:00 level=WARN source=ggml.go:149 msg="key not found" key=llama.attention.key_length default=128 time=2025-04-06T01:46:58.440+08:00 level=WARN source=ggml.go:149 msg="key not found" key=llama.attention.value_length default=128 time=2025-04-06T01:46:58.441+08:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[44.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="6.5 GiB" memory.required.partial="6.5 GiB" memory.required.kv="1.0 GiB" memory.required.allocations="[6.5 GiB]" memory.weights.total="4.3 GiB" memory.weights.repeating="3.9 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="677.5 MiB" llama_model_loader: loaded meta data with 29 key-value pairs and 292 tensors from /home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Meta Llama 3.1 8B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Meta-Llama-3.1 llama_model_loader: - kv 5: general.size_label str = 8B llama_model_loader: - kv 6: general.license str = llama3.1 llama_model_loader: - kv 7: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam... llama_model_loader: - kv 8: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ... llama_model_loader: - kv 9: llama.block_count u32 = 32 llama_model_loader: - kv 10: llama.context_length u32 = 131072 llama_model_loader: - kv 11: llama.embedding_length u32 = 4096 llama_model_loader: - kv 12: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 13: llama.attention.head_count u32 = 32 llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 17: general.file_type u32 = 15 llama_model_loader: - kv 18: llama.vocab_size u32 = 128256 llama_model_loader: - kv 19: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 20: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 21: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 24: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 25: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 27: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ... llama_model_loader: - kv 28: general.quantization_version u32 = 2 llama_model_loader: - type f32: 66 tensors llama_model_loader: - type q4_K: 193 tensors llama_model_loader: - type q6_K: 33 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 4.58 GiB (4.89 BPW) load: special tokens cache size = 256 load: token to piece cache size = 0.7999 MB print_info: arch = llama print_info: vocab_only = 1 print_info: model type = ?B print_info: model params = 8.03 B print_info: general.name = Meta Llama 3.1 8B Instruct print_info: vocab type = BPE print_info: n_vocab = 128256 print_info: n_merges = 280147 print_info: BOS token = 128000 '<|begin_of_text|>' print_info: EOS token = 128009 '<|eot_id|>' print_info: EOT token = 128009 '<|eot_id|>' print_info: EOM token = 128008 '<|eom_id|>' print_info: LF token = 198 'Ċ' print_info: EOG token = 128008 '<|eom_id|>' print_info: EOG token = 128009 '<|eot_id|>' print_info: max token length = 256 llama_model_load: vocab only - skipping tensors time=2025-04-06T01:46:58.704+08:00 level=INFO source=server.go:405 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 --ctx-size 8192 --batch-size 512 --n-gpu-layers 33 --threads 32 --parallel 4 --port 35977" time=2025-04-06T01:46:58.707+08:00 level=INFO source=sched.go:451 msg="loaded runners" count=1 time=2025-04-06T01:46:58.707+08:00 level=INFO source=server.go:580 msg="waiting for llama runner to start responding" time=2025-04-06T01:46:58.707+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error" time=2025-04-06T01:46:58.725+08:00 level=INFO source=runner.go:858 msg="starting go runner" time=2025-04-06T01:46:58.725+08:00 level=INFO source=ggml.go:109 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) time=2025-04-06T01:46:58.727+08:00 level=INFO source=runner.go:918 msg="Server listening on 127.0.0.1:35977" llama_model_loader: loaded meta data with 29 key-value pairs and 292 tensors from /home/chenjy/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Meta Llama 3.1 8B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Meta-Llama-3.1 llama_model_loader: - kv 5: general.size_label str = 8B llama_model_loader: - kv 6: general.license str = llama3.1 llama_model_loader: - kv 7: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam... llama_model_loader: - kv 8: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ... llama_model_loader: - kv 9: llama.block_count u32 = 32 llama_model_loader: - kv 10: llama.context_length u32 = 131072 llama_model_loader: - kv 11: llama.embedding_length u32 = 4096 llama_model_loader: - kv 12: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 13: llama.attention.head_count u32 = 32 llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 17: general.file_type u32 = 15 llama_model_loader: - kv 18: llama.vocab_size u32 = 128256 llama_model_loader: - kv 19: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 20: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 21: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 24: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 25: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 27: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ... llama_model_loader: - kv 28: general.quantization_version u32 = 2 llama_model_loader: - type f32: 66 tensors llama_model_loader: - type q4_K: 193 tensors llama_model_loader: - type q6_K: 33 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 4.58 GiB (4.89 BPW) load: special tokens cache size = 256 time=2025-04-06T01:46:58.961+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model" Not a single response in five minutes. The latest v0.6.4 version is also very slow, is there anyone who can tell me why?
GiteaMirror commented 2026-04-12 18:20:58 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Apr 5, 2025):

Can you try to zip some files to free up some space. Or remove llama3.1 and load a smaller model like llama3.2

<!-- gh-comment-id:2781092363 --> @igorschlum commented on GitHub (Apr 5, 2025): Can you try to zip some files to free up some space. Or remove llama3.1 and load a smaller model like llama3.2
GiteaMirror commented 2026-04-12 18:20:59 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Apr 6, 2025):

it worked?

<!-- gh-comment-id:2781402441 --> @igorschlum commented on GitHub (Apr 6, 2025): it worked?
GiteaMirror commented 2026-04-12 18:21:00 -05:00
Author
Owner
Copy Link

@bravelyi commented on GitHub (Apr 6, 2025):

Thank you very much, I have solved the problem, follow the official website to download, manually download and install the problem!

<!-- gh-comment-id:2781434487 --> @bravelyi commented on GitHub (Apr 6, 2025): Thank you very much, I have solved the problem, follow the official website to download, manually download and install the problem!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label model
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#6654
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?