github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5850] Error loading model on 0.2.8-rc1-rocm #50161

New Issue
Closed
opened 2026-04-28 14:27:59 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 14:27:59 -05:00
Owner
Copy Link

Originally created by @dvelez3815 on GitHub (Jul 22, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5850

What is the issue?

segmentation fault (core dumped) error

2024/07/22 13:17:50 routes.go:1100: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:/root/.ollama/models 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://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-07-22T13:17:50.145Z level=INFO source=images.go:784 msg="total blobs: 23"
time=2024-07-22T13:17:50.145Z level=INFO source=images.go:791 msg="total unused blobs removed: 0"
time=2024-07-22T13:17:50.145Z level=INFO source=routes.go:1147 msg="Listening on [::]:11434 (version 0.2.8-rc1)"
time=2024-07-22T13:17:50.145Z level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama2936133361/runners
time=2024-07-22T13:17:51.862Z level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11 rocm_v60102]"
time=2024-07-22T13:17:51.862Z level=INFO source=gpu.go:205 msg="looking for compatible GPUs"
time=2024-07-22T13:17:51.867Z level=INFO source=amd_linux.go:330 msg="amdgpu is supported" gpu=0 gpu_type=gfx1100
time=2024-07-22T13:17:51.868Z level=INFO source=amd_linux.go:330 msg="amdgpu is supported" gpu=1 gpu_type=gfx1100
time=2024-07-22T13:17:51.869Z level=INFO source=amd_linux.go:330 msg="amdgpu is supported" gpu=2 gpu_type=gfx1100
time=2024-07-22T13:17:51.869Z level=INFO source=amd_linux.go:259 msg="unsupported Radeon iGPU detected skipping" id=3 total="512.0 MiB"
time=2024-07-22T13:17:51.869Z level=INFO source=types.go:105 msg="inference compute" id=0 library=rocm compute=gfx1100 driver=6.7 name=1002:744c total="24.0 GiB" available="24.0 GiB"
time=2024-07-22T13:17:51.869Z level=INFO source=types.go:105 msg="inference compute" id=1 library=rocm compute=gfx1100 driver=6.7 name=1002:744c total="24.0 GiB" available="24.0 GiB"
time=2024-07-22T13:17:51.869Z level=INFO source=types.go:105 msg="inference compute" id=2 library=rocm compute=gfx1100 driver=6.7 name=1002:744c total="24.0 GiB" available="24.0 GiB"
[GIN] 2024/07/22 - 13:18:52 | 200 |      30.718µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/07/22 - 13:18:52 | 200 |     713.463µs |       127.0.0.1 | GET      "/api/tags"
[GIN] 2024/07/22 - 13:19:01 | 200 |      17.853µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/07/22 - 13:19:01 | 200 |    15.69545ms |       127.0.0.1 | POST     "/api/show"
time=2024-07-22T13:19:01.124Z level=INFO source=sched.go:717 msg="new model will fit in available VRAM, loading" model=/root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72 library=rocm parallel=4 required="45.3 GiB"
time=2024-07-22T13:19:01.125Z level=INFO source=memory.go:309 msg="offload to rocm" layers.requested=-1 layers.model=33 layers.offload=33 layers.split=11,11,11 memory.available="[24.0 GiB 24.0 GiB 24.0 GiB]" memory.required.full="45.3 GiB" memory.required.partial="45.3 GiB" memory.required.kv="1.0 GiB" memory.required.allocations="[15.4 GiB 15.4 GiB 14.4 GiB]" memory.weights.total="36.5 GiB" memory.weights.repeating="36.4 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="1.3 GiB" memory.graph.partial="1.3 GiB"
time=2024-07-22T13:19:01.125Z level=INFO source=server.go:383 msg="starting llama server" cmd="/tmp/ollama2936133361/runners/rocm_v60102/ollama_llama_server --model /root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72 --ctx-size 8192 --batch-size 512 --embedding --log-disable --n-gpu-layers 33 --parallel 4 --tensor-split 11,11,11 --port 37323"
time=2024-07-22T13:19:01.125Z level=INFO source=sched.go:437 msg="loaded runners" count=1
time=2024-07-22T13:19:01.126Z level=INFO source=server.go:573 msg="waiting for llama runner to start responding"
time=2024-07-22T13:19:01.126Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error"
INFO [main] build info | build=1 commit="a8db2a9" tid="127915017311040" timestamp=1721654341
INFO [main] system info | n_threads=16 n_threads_batch=-1 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 0 | " tid="127915017311040" timestamp=1721654341 total_threads=32
INFO [main] HTTP server listening | hostname="127.0.0.1" n_threads_http="31" port="37323" tid="127915017311040" timestamp=1721654341
llama_model_loader: loaded meta data with 26 key-value pairs and 995 tensors from /root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72 (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              = mistralai
llama_model_loader: - kv   2:                       llama.context_length u32              = 32768
llama_model_loader: - kv   3:                     llama.embedding_length u32              = 4096
llama_model_loader: - kv   4:                          llama.block_count u32              = 32
llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 14336
llama_model_loader: - kv   6:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv   7:                 llama.attention.head_count u32              = 32
llama_model_loader: - kv   8:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv   9:                         llama.expert_count u32              = 8
llama_model_loader: - kv  10:                    llama.expert_used_count u32              = 2
llama_model_loader: - kv  11:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  12:                       llama.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  13:                          general.file_type u32              = 18
llama_model_loader: - kv  14:                       tokenizer.ggml.model str              = llama
llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,32000]   = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv  16:                      tokenizer.ggml.scores arr[f32,32000]   = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv  17:                  tokenizer.ggml.token_type arr[i32,32000]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv  18:                      tokenizer.ggml.merges arr[str,58980]   = ["▁ t", "i n", "e r", "▁ a", "h e...
llama_model_loader: - kv  19:                tokenizer.ggml.bos_token_id u32              = 1
llama_model_loader: - kv  20:                tokenizer.ggml.eos_token_id u32              = 2
llama_model_loader: - kv  21:            tokenizer.ggml.unknown_token_id u32              = 0
llama_model_loader: - kv  22:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  23:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  24:                    tokenizer.chat_template str              = {{ bos_token }}{% for message in mess...
llama_model_loader: - kv  25:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type  f16:   32 tensors
llama_model_loader: - type q8_0:   64 tensors
llama_model_loader: - type q6_K:  834 tensors
llm_load_vocab: special tokens cache size = 259
llm_load_vocab: token to piece cache size = 0.1637 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = SPM
llm_load_print_meta: n_vocab          = 32000
llm_load_print_meta: n_merges         = 0
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 32768
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         = 8
llm_load_print_meta: n_expert_used    = 2
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  = 1000000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn  = 32768
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: model type       = 8x7B
llm_load_print_meta: model ftype      = Q6_K
llm_load_print_meta: model params     = 46.70 B
llm_load_print_meta: model size       = 35.74 GiB (6.57 BPW) 
llm_load_print_meta: general.name     = mistralai
llm_load_print_meta: BOS token        = 1 '<s>'
llm_load_print_meta: EOS token        = 2 '</s>'
llm_load_print_meta: UNK token        = 0 '<unk>'
llm_load_print_meta: LF token         = 13 '<0x0A>'
llm_load_print_meta: max token length = 48
time=2024-07-22T13:19:01.377Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model"
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 3 ROCm devices:
  Device 0: Radeon RX 7900 XTX, compute capability 11.0, VMM: no
  Device 1: Radeon RX 7900 XTX, compute capability 11.0, VMM: no
  Device 2: Radeon RX 7900 XTX, compute capability 11.0, VMM: no
llm_load_tensors: ggml ctx size =    1.53 MiB
time=2024-07-22T13:19:05.338Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server not responding"
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 33/33 layers to GPU
llm_load_tensors:      ROCm0 buffer size = 12510.78 MiB
llm_load_tensors:      ROCm1 buffer size = 12510.78 MiB
llm_load_tensors:      ROCm2 buffer size = 11475.99 MiB
llm_load_tensors:  ROCm_Host buffer size =   102.54 MiB
time=2024-07-22T13:19:05.590Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model"
time=2024-07-22T13:19:15.818Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server not responding"
time=2024-07-22T13:19:16.646Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model"
llama_new_context_with_model: n_ctx      = 8192
llama_new_context_with_model: n_batch    = 512
llama_new_context_with_model: n_ubatch   = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base  = 1000000.0
llama_new_context_with_model: freq_scale = 1
time=2024-07-22T13:19:18.099Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server not responding"
time=2024-07-22T13:19:18.912Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model"
llama_kv_cache_init:      ROCm0 KV buffer size =   352.00 MiB
llama_kv_cache_init:      ROCm1 KV buffer size =   352.00 MiB
llama_kv_cache_init:      ROCm2 KV buffer size =   320.00 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:  ROCm_Host  output buffer size =     0.55 MiB
llama_new_context_with_model: pipeline parallelism enabled (n_copies=4)
llama_new_context_with_model:      ROCm0 compute buffer size =   640.01 MiB
llama_new_context_with_model:      ROCm1 compute buffer size =   640.01 MiB
llama_new_context_with_model:      ROCm2 compute buffer size =   640.02 MiB
llama_new_context_with_model:  ROCm_Host compute buffer size =    72.02 MiB
llama_new_context_with_model: graph nodes  = 1510
llama_new_context_with_model: graph splits = 4
time=2024-07-22T13:19:20.722Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error"
time=2024-07-22T13:19:20.973Z level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: signal: segmentation fault (core dumped) "
[GIN] 2024/07/22 - 13:19:20 | 500 | 19.864840905s |       127.0.0.1 | POST     "/api/chat"
time=2024-07-22T13:19:25.973Z level=WARN source=sched.go:634 msg="gpu VRAM usage didn't recover within timeout" seconds=5.000268374 model=/root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72
time=2024-07-22T13:19:26.224Z level=WARN source=sched.go:634 msg="gpu VRAM usage didn't recover within timeout" seconds=5.250851195 model=/root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72
time=2024-07-22T13:19:26.473Z level=WARN source=sched.go:634 msg="gpu VRAM usage didn't recover within timeout" seconds=5.500499856 model=/root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.2.8-rc1-rocm

Originally created by @dvelez3815 on GitHub (Jul 22, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5850 ### What is the issue? segmentation fault (core dumped) error ``` 2024/07/22 13:17:50 routes.go:1100: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:/root/.ollama/models 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://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-07-22T13:17:50.145Z level=INFO source=images.go:784 msg="total blobs: 23" time=2024-07-22T13:17:50.145Z level=INFO source=images.go:791 msg="total unused blobs removed: 0" time=2024-07-22T13:17:50.145Z level=INFO source=routes.go:1147 msg="Listening on [::]:11434 (version 0.2.8-rc1)" time=2024-07-22T13:17:50.145Z level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama2936133361/runners time=2024-07-22T13:17:51.862Z level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11 rocm_v60102]" time=2024-07-22T13:17:51.862Z level=INFO source=gpu.go:205 msg="looking for compatible GPUs" time=2024-07-22T13:17:51.867Z level=INFO source=amd_linux.go:330 msg="amdgpu is supported" gpu=0 gpu_type=gfx1100 time=2024-07-22T13:17:51.868Z level=INFO source=amd_linux.go:330 msg="amdgpu is supported" gpu=1 gpu_type=gfx1100 time=2024-07-22T13:17:51.869Z level=INFO source=amd_linux.go:330 msg="amdgpu is supported" gpu=2 gpu_type=gfx1100 time=2024-07-22T13:17:51.869Z level=INFO source=amd_linux.go:259 msg="unsupported Radeon iGPU detected skipping" id=3 total="512.0 MiB" time=2024-07-22T13:17:51.869Z level=INFO source=types.go:105 msg="inference compute" id=0 library=rocm compute=gfx1100 driver=6.7 name=1002:744c total="24.0 GiB" available="24.0 GiB" time=2024-07-22T13:17:51.869Z level=INFO source=types.go:105 msg="inference compute" id=1 library=rocm compute=gfx1100 driver=6.7 name=1002:744c total="24.0 GiB" available="24.0 GiB" time=2024-07-22T13:17:51.869Z level=INFO source=types.go:105 msg="inference compute" id=2 library=rocm compute=gfx1100 driver=6.7 name=1002:744c total="24.0 GiB" available="24.0 GiB" [GIN] 2024/07/22 - 13:18:52 | 200 | 30.718µs | 127.0.0.1 | HEAD "/" [GIN] 2024/07/22 - 13:18:52 | 200 | 713.463µs | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/22 - 13:19:01 | 200 | 17.853µs | 127.0.0.1 | HEAD "/" [GIN] 2024/07/22 - 13:19:01 | 200 | 15.69545ms | 127.0.0.1 | POST "/api/show" time=2024-07-22T13:19:01.124Z level=INFO source=sched.go:717 msg="new model will fit in available VRAM, loading" model=/root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72 library=rocm parallel=4 required="45.3 GiB" time=2024-07-22T13:19:01.125Z level=INFO source=memory.go:309 msg="offload to rocm" layers.requested=-1 layers.model=33 layers.offload=33 layers.split=11,11,11 memory.available="[24.0 GiB 24.0 GiB 24.0 GiB]" memory.required.full="45.3 GiB" memory.required.partial="45.3 GiB" memory.required.kv="1.0 GiB" memory.required.allocations="[15.4 GiB 15.4 GiB 14.4 GiB]" memory.weights.total="36.5 GiB" memory.weights.repeating="36.4 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="1.3 GiB" memory.graph.partial="1.3 GiB" time=2024-07-22T13:19:01.125Z level=INFO source=server.go:383 msg="starting llama server" cmd="/tmp/ollama2936133361/runners/rocm_v60102/ollama_llama_server --model /root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72 --ctx-size 8192 --batch-size 512 --embedding --log-disable --n-gpu-layers 33 --parallel 4 --tensor-split 11,11,11 --port 37323" time=2024-07-22T13:19:01.125Z level=INFO source=sched.go:437 msg="loaded runners" count=1 time=2024-07-22T13:19:01.126Z level=INFO source=server.go:573 msg="waiting for llama runner to start responding" time=2024-07-22T13:19:01.126Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error" INFO [main] build info | build=1 commit="a8db2a9" tid="127915017311040" timestamp=1721654341 INFO [main] system info | n_threads=16 n_threads_batch=-1 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 0 | " tid="127915017311040" timestamp=1721654341 total_threads=32 INFO [main] HTTP server listening | hostname="127.0.0.1" n_threads_http="31" port="37323" tid="127915017311040" timestamp=1721654341 llama_model_loader: loaded meta data with 26 key-value pairs and 995 tensors from /root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72 (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 = mistralai llama_model_loader: - kv 2: llama.context_length u32 = 32768 llama_model_loader: - kv 3: llama.embedding_length u32 = 4096 llama_model_loader: - kv 4: llama.block_count u32 = 32 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 7: llama.attention.head_count u32 = 32 llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 9: llama.expert_count u32 = 8 llama_model_loader: - kv 10: llama.expert_used_count u32 = 2 llama_model_loader: - kv 11: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 12: llama.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 13: general.file_type u32 = 18 llama_model_loader: - kv 14: tokenizer.ggml.model str = llama llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<... llama_model_loader: - kv 16: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... llama_model_loader: - kv 18: tokenizer.ggml.merges arr[str,58980] = ["▁ t", "i n", "e r", "▁ a", "h e... llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 21: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 24: tokenizer.chat_template str = {{ bos_token }}{% for message in mess... llama_model_loader: - kv 25: general.quantization_version u32 = 2 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type f16: 32 tensors llama_model_loader: - type q8_0: 64 tensors llama_model_loader: - type q6_K: 834 tensors llm_load_vocab: special tokens cache size = 259 llm_load_vocab: token to piece cache size = 0.1637 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = SPM llm_load_print_meta: n_vocab = 32000 llm_load_print_meta: n_merges = 0 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 32768 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 = 8 llm_load_print_meta: n_expert_used = 2 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 = 1000000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 32768 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: model type = 8x7B llm_load_print_meta: model ftype = Q6_K llm_load_print_meta: model params = 46.70 B llm_load_print_meta: model size = 35.74 GiB (6.57 BPW) llm_load_print_meta: general.name = mistralai llm_load_print_meta: BOS token = 1 '<s>' llm_load_print_meta: EOS token = 2 '</s>' llm_load_print_meta: UNK token = 0 '<unk>' llm_load_print_meta: LF token = 13 '<0x0A>' llm_load_print_meta: max token length = 48 time=2024-07-22T13:19:01.377Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model" ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 3 ROCm devices: Device 0: Radeon RX 7900 XTX, compute capability 11.0, VMM: no Device 1: Radeon RX 7900 XTX, compute capability 11.0, VMM: no Device 2: Radeon RX 7900 XTX, compute capability 11.0, VMM: no llm_load_tensors: ggml ctx size = 1.53 MiB time=2024-07-22T13:19:05.338Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server not responding" llm_load_tensors: offloading 32 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 33/33 layers to GPU llm_load_tensors: ROCm0 buffer size = 12510.78 MiB llm_load_tensors: ROCm1 buffer size = 12510.78 MiB llm_load_tensors: ROCm2 buffer size = 11475.99 MiB llm_load_tensors: ROCm_Host buffer size = 102.54 MiB time=2024-07-22T13:19:05.590Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model" time=2024-07-22T13:19:15.818Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server not responding" time=2024-07-22T13:19:16.646Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model" llama_new_context_with_model: n_ctx = 8192 llama_new_context_with_model: n_batch = 512 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 1000000.0 llama_new_context_with_model: freq_scale = 1 time=2024-07-22T13:19:18.099Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server not responding" time=2024-07-22T13:19:18.912Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model" llama_kv_cache_init: ROCm0 KV buffer size = 352.00 MiB llama_kv_cache_init: ROCm1 KV buffer size = 352.00 MiB llama_kv_cache_init: ROCm2 KV buffer size = 320.00 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: ROCm_Host output buffer size = 0.55 MiB llama_new_context_with_model: pipeline parallelism enabled (n_copies=4) llama_new_context_with_model: ROCm0 compute buffer size = 640.01 MiB llama_new_context_with_model: ROCm1 compute buffer size = 640.01 MiB llama_new_context_with_model: ROCm2 compute buffer size = 640.02 MiB llama_new_context_with_model: ROCm_Host compute buffer size = 72.02 MiB llama_new_context_with_model: graph nodes = 1510 llama_new_context_with_model: graph splits = 4 time=2024-07-22T13:19:20.722Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error" time=2024-07-22T13:19:20.973Z level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: signal: segmentation fault (core dumped) " [GIN] 2024/07/22 - 13:19:20 | 500 | 19.864840905s | 127.0.0.1 | POST "/api/chat" time=2024-07-22T13:19:25.973Z level=WARN source=sched.go:634 msg="gpu VRAM usage didn't recover within timeout" seconds=5.000268374 model=/root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72 time=2024-07-22T13:19:26.224Z level=WARN source=sched.go:634 msg="gpu VRAM usage didn't recover within timeout" seconds=5.250851195 model=/root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72 time=2024-07-22T13:19:26.473Z level=WARN source=sched.go:634 msg="gpu VRAM usage didn't recover within timeout" seconds=5.500499856 model=/root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72 ``` ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.2.8-rc1-rocm
GiteaMirror added the bugamd labels 2026-04-28 14:27:59 -05:00
GiteaMirror commented 2026-04-28 14:28:07 -05:00
Author
Owner
Copy Link

@dvelez3815 commented on GitHub (Jul 22, 2024):

On other version (1.44) is kinda okay but I got trash response...

2024/07/22 13:23:13 routes.go:1011: INFO server config env="map[OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE: OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:/root/.ollama/models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 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://*] OLLAMA_RUNNERS_DIR: OLLAMA_TMPDIR:]"
time=2024-07-22T13:23:13.315Z level=INFO source=images.go:725 msg="total blobs: 23"
time=2024-07-22T13:23:13.315Z level=INFO source=images.go:732 msg="total unused blobs removed: 0"
time=2024-07-22T13:23:13.316Z level=INFO source=routes.go:1057 msg="Listening on [::]:11434 (version 0.1.44)"
time=2024-07-22T13:23:13.316Z level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama432537499/runners
time=2024-07-22T13:23:15.795Z level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cuda_v11 rocm_v60002 cpu cpu_avx cpu_avx2]"
time=2024-07-22T13:23:15.800Z level=INFO source=amd_linux.go:301 msg="amdgpu is supported" gpu=0 gpu_type=gfx1100
time=2024-07-22T13:23:15.800Z level=INFO source=amd_linux.go:301 msg="amdgpu is supported" gpu=1 gpu_type=gfx1100
time=2024-07-22T13:23:15.800Z level=INFO source=amd_linux.go:301 msg="amdgpu is supported" gpu=2 gpu_type=gfx1100
time=2024-07-22T13:23:15.800Z level=INFO source=amd_linux.go:233 msg="unsupported Radeon iGPU detected skipping" id=3 total="512.0 MiB"
time=2024-07-22T13:23:15.800Z level=INFO source=types.go:71 msg="inference compute" id=0 library=rocm compute=gfx1100 driver=6.7 name=1002:744c total="24.0 GiB" available="24.0 GiB"
time=2024-07-22T13:23:15.800Z level=INFO source=types.go:71 msg="inference compute" id=1 library=rocm compute=gfx1100 driver=6.7 name=1002:744c total="24.0 GiB" available="24.0 GiB"
time=2024-07-22T13:23:15.800Z level=INFO source=types.go:71 msg="inference compute" id=2 library=rocm compute=gfx1100 driver=6.7 name=1002:744c total="24.0 GiB" available="24.0 GiB"
[GIN] 2024/07/22 - 13:23:23 | 200 |      25.789µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/07/22 - 13:23:23 | 200 |      557.66µs |       127.0.0.1 | GET      "/api/tags"
[GIN] 2024/07/22 - 13:23:30 | 200 |       21.14µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/07/22 - 13:23:30 | 200 |     643.581µs |       127.0.0.1 | POST     "/api/show"
[GIN] 2024/07/22 - 13:23:30 | 200 |     252.565µs |       127.0.0.1 | POST     "/api/show"
time=2024-07-22T13:23:30.273Z level=INFO source=amd_linux.go:301 msg="amdgpu is supported" gpu=0 gpu_type=gfx1100
time=2024-07-22T13:23:30.273Z level=INFO source=amd_linux.go:301 msg="amdgpu is supported" gpu=1 gpu_type=gfx1100
time=2024-07-22T13:23:30.273Z level=INFO source=amd_linux.go:301 msg="amdgpu is supported" gpu=2 gpu_type=gfx1100
time=2024-07-22T13:23:30.273Z level=INFO source=amd_linux.go:233 msg="unsupported Radeon iGPU detected skipping" id=3 total="512.0 MiB"
time=2024-07-22T13:23:30.493Z level=INFO source=memory.go:133 msg="offload to gpu" layers.requested=-1 layers.real=19 memory.available="24.0 GiB" memory.required.full="37.6 GiB" memory.required.partial="23.7 GiB" memory.required.kv="256.0 MiB" memory.weights.total="35.6 GiB" memory.weights.repeating="35.5 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="184.0 MiB" memory.graph.partial="935.0 MiB"
time=2024-07-22T13:23:30.494Z level=INFO source=memory.go:133 msg="offload to gpu" layers.requested=-1 layers.real=19 memory.available="24.0 GiB" memory.required.full="37.6 GiB" memory.required.partial="23.7 GiB" memory.required.kv="256.0 MiB" memory.weights.total="35.6 GiB" memory.weights.repeating="35.5 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="184.0 MiB" memory.graph.partial="935.0 MiB"
time=2024-07-22T13:23:30.495Z level=INFO source=memory.go:133 msg="offload to gpu" layers.requested=-1 layers.real=19 memory.available="24.0 GiB" memory.required.full="37.6 GiB" memory.required.partial="23.7 GiB" memory.required.kv="256.0 MiB" memory.weights.total="35.6 GiB" memory.weights.repeating="35.5 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="184.0 MiB" memory.graph.partial="935.0 MiB"
time=2024-07-22T13:23:30.496Z level=INFO source=memory.go:133 msg="offload to gpu" layers.requested=-1 layers.real=33 memory.available="71.9 GiB" memory.required.full="38.0 GiB" memory.required.partial="38.0 GiB" memory.required.kv="256.0 MiB" memory.weights.total="35.6 GiB" memory.weights.repeating="35.5 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="552.1 MiB" memory.graph.partial="2.7 GiB"
time=2024-07-22T13:23:30.497Z level=INFO source=memory.go:133 msg="offload to gpu" layers.requested=-1 layers.real=33 memory.available="71.9 GiB" memory.required.full="38.0 GiB" memory.required.partial="38.0 GiB" memory.required.kv="256.0 MiB" memory.weights.total="35.6 GiB" memory.weights.repeating="35.5 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="552.1 MiB" memory.graph.partial="2.7 GiB"
time=2024-07-22T13:23:30.498Z level=INFO source=server.go:341 msg="starting llama server" cmd="/tmp/ollama432537499/runners/rocm_v60002/ollama_llama_server --model /root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72 --ctx-size 2048 --batch-size 512 --embedding --log-disable --n-gpu-layers 33 --parallel 1 --port 39509"
time=2024-07-22T13:23:30.498Z level=INFO source=sched.go:338 msg="loaded runners" count=1
time=2024-07-22T13:23:30.498Z level=INFO source=server.go:529 msg="waiting for llama runner to start responding"
time=2024-07-22T13:23:30.498Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server error"
INFO [main] build info | build=1 commit="5921b8f" tid="136304919219264" timestamp=1721654610
INFO [main] system info | n_threads=16 n_threads_batch=-1 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | " tid="136304919219264" timestamp=1721654610 total_threads=32
INFO [main] HTTP server listening | hostname="127.0.0.1" n_threads_http="31" port="39509" tid="136304919219264" timestamp=1721654610
llama_model_loader: loaded meta data with 26 key-value pairs and 995 tensors from /root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72 (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              = mistralai
llama_model_loader: - kv   2:                       llama.context_length u32              = 32768
llama_model_loader: - kv   3:                     llama.embedding_length u32              = 4096
llama_model_loader: - kv   4:                          llama.block_count u32              = 32
llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 14336
llama_model_loader: - kv   6:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv   7:                 llama.attention.head_count u32              = 32
llama_model_loader: - kv   8:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv   9:                         llama.expert_count u32              = 8
llama_model_loader: - kv  10:                    llama.expert_used_count u32              = 2
llama_model_loader: - kv  11:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  12:                       llama.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  13:                          general.file_type u32              = 18
llama_model_loader: - kv  14:                       tokenizer.ggml.model str              = llama
llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,32000]   = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv  16:                      tokenizer.ggml.scores arr[f32,32000]   = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv  17:                  tokenizer.ggml.token_type arr[i32,32000]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv  18:                      tokenizer.ggml.merges arr[str,58980]   = ["▁ t", "i n", "e r", "▁ a", "h e...
llama_model_loader: - kv  19:                tokenizer.ggml.bos_token_id u32              = 1
llama_model_loader: - kv  20:                tokenizer.ggml.eos_token_id u32              = 2
llama_model_loader: - kv  21:            tokenizer.ggml.unknown_token_id u32              = 0
llama_model_loader: - kv  22:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  23:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  24:                    tokenizer.chat_template str              = {{ bos_token }}{% for message in mess...
llama_model_loader: - kv  25:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type  f16:   32 tensors
llama_model_loader: - type q8_0:   64 tensors
llama_model_loader: - type q6_K:  834 tensors
llm_load_vocab: special tokens cache size = 259
llm_load_vocab: token to piece cache size = 0.3274 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = SPM
llm_load_print_meta: n_vocab          = 32000
llm_load_print_meta: n_merges         = 0
llm_load_print_meta: n_ctx_train      = 32768
llm_load_print_meta: n_embd           = 4096
llm_load_print_meta: n_head           = 32
llm_load_print_meta: n_head_kv        = 8
llm_load_print_meta: n_layer          = 32
llm_load_print_meta: n_rot            = 128
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         = 8
llm_load_print_meta: n_expert_used    = 2
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  = 1000000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx  = 32768
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: model type       = 8x7B
llm_load_print_meta: model ftype      = Q6_K
llm_load_print_meta: model params     = 46.70 B
llm_load_print_meta: model size       = 35.74 GiB (6.57 BPW) 
llm_load_print_meta: general.name     = mistralai
llm_load_print_meta: BOS token        = 1 '<s>'
llm_load_print_meta: EOS token        = 2 '</s>'
llm_load_print_meta: UNK token        = 0 '<unk>'
llm_load_print_meta: LF token         = 13 '<0x0A>'
time=2024-07-22T13:23:30.749Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server loading model"
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:   no
ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
ggml_cuda_init: found 3 ROCm devices:
  Device 0: Radeon RX 7900 XTX, compute capability 11.0, VMM: no
  Device 1: Radeon RX 7900 XTX, compute capability 11.0, VMM: no
  Device 2: Radeon RX 7900 XTX, compute capability 11.0, VMM: no
llm_load_tensors: ggml ctx size =    1.67 MiB
time=2024-07-22T13:23:34.710Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server not responding"
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 33/33 layers to GPU
llm_load_tensors:      ROCm0 buffer size = 12510.78 MiB
llm_load_tensors:      ROCm1 buffer size = 12510.78 MiB
llm_load_tensors:      ROCm2 buffer size = 11475.99 MiB
llm_load_tensors:  ROCm_Host buffer size =   102.54 MiB
time=2024-07-22T13:23:35.412Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server loading model"
time=2024-07-22T13:23:45.648Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server not responding"
time=2024-07-22T13:23:46.518Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server loading model"
llama_new_context_with_model: n_ctx      = 2048
llama_new_context_with_model: n_batch    = 512
llama_new_context_with_model: n_ubatch   = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base  = 1000000.0
llama_new_context_with_model: freq_scale = 1
time=2024-07-22T13:23:47.972Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server not responding"
time=2024-07-22T13:23:48.334Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server loading model"
llama_kv_cache_init:      ROCm0 KV buffer size =    88.00 MiB
llama_kv_cache_init:      ROCm1 KV buffer size =    88.00 MiB
llama_kv_cache_init:      ROCm2 KV buffer size =    80.00 MiB
llama_new_context_with_model: KV self size  =  256.00 MiB, K (f16):  128.00 MiB, V (f16):  128.00 MiB
llama_new_context_with_model:  ROCm_Host  output buffer size =     0.14 MiB
llama_new_context_with_model: pipeline parallelism enabled (n_copies=4)
llama_new_context_with_model:      ROCm0 compute buffer size =   208.01 MiB
llama_new_context_with_model:      ROCm1 compute buffer size =   208.01 MiB
llama_new_context_with_model:      ROCm2 compute buffer size =   208.02 MiB
llama_new_context_with_model:  ROCm_Host compute buffer size =    24.02 MiB
llama_new_context_with_model: graph nodes  = 1510
llama_new_context_with_model: graph splits = 4
INFO [main] model loaded | tid="136304919219264" timestamp=1721654631
time=2024-07-22T13:23:51.845Z level=INFO source=server.go:572 msg="llama runner started in 21.35 seconds"
[GIN] 2024/07/22 - 13:23:51 | 200 | 21.576923759s |       127.0.0.1 | POST     "/api/chat"

chat:

>>> hi
###############################

>>> Send a message (/? for help)
``
<!-- gh-comment-id:2242956638 --> @dvelez3815 commented on GitHub (Jul 22, 2024): On other version (1.44) is kinda okay but I got trash response... ``` 2024/07/22 13:23:13 routes.go:1011: INFO server config env="map[OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE: OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:/root/.ollama/models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 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://*] OLLAMA_RUNNERS_DIR: OLLAMA_TMPDIR:]" time=2024-07-22T13:23:13.315Z level=INFO source=images.go:725 msg="total blobs: 23" time=2024-07-22T13:23:13.315Z level=INFO source=images.go:732 msg="total unused blobs removed: 0" time=2024-07-22T13:23:13.316Z level=INFO source=routes.go:1057 msg="Listening on [::]:11434 (version 0.1.44)" time=2024-07-22T13:23:13.316Z level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama432537499/runners time=2024-07-22T13:23:15.795Z level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cuda_v11 rocm_v60002 cpu cpu_avx cpu_avx2]" time=2024-07-22T13:23:15.800Z level=INFO source=amd_linux.go:301 msg="amdgpu is supported" gpu=0 gpu_type=gfx1100 time=2024-07-22T13:23:15.800Z level=INFO source=amd_linux.go:301 msg="amdgpu is supported" gpu=1 gpu_type=gfx1100 time=2024-07-22T13:23:15.800Z level=INFO source=amd_linux.go:301 msg="amdgpu is supported" gpu=2 gpu_type=gfx1100 time=2024-07-22T13:23:15.800Z level=INFO source=amd_linux.go:233 msg="unsupported Radeon iGPU detected skipping" id=3 total="512.0 MiB" time=2024-07-22T13:23:15.800Z level=INFO source=types.go:71 msg="inference compute" id=0 library=rocm compute=gfx1100 driver=6.7 name=1002:744c total="24.0 GiB" available="24.0 GiB" time=2024-07-22T13:23:15.800Z level=INFO source=types.go:71 msg="inference compute" id=1 library=rocm compute=gfx1100 driver=6.7 name=1002:744c total="24.0 GiB" available="24.0 GiB" time=2024-07-22T13:23:15.800Z level=INFO source=types.go:71 msg="inference compute" id=2 library=rocm compute=gfx1100 driver=6.7 name=1002:744c total="24.0 GiB" available="24.0 GiB" [GIN] 2024/07/22 - 13:23:23 | 200 | 25.789µs | 127.0.0.1 | HEAD "/" [GIN] 2024/07/22 - 13:23:23 | 200 | 557.66µs | 127.0.0.1 | GET "/api/tags" [GIN] 2024/07/22 - 13:23:30 | 200 | 21.14µs | 127.0.0.1 | HEAD "/" [GIN] 2024/07/22 - 13:23:30 | 200 | 643.581µs | 127.0.0.1 | POST "/api/show" [GIN] 2024/07/22 - 13:23:30 | 200 | 252.565µs | 127.0.0.1 | POST "/api/show" time=2024-07-22T13:23:30.273Z level=INFO source=amd_linux.go:301 msg="amdgpu is supported" gpu=0 gpu_type=gfx1100 time=2024-07-22T13:23:30.273Z level=INFO source=amd_linux.go:301 msg="amdgpu is supported" gpu=1 gpu_type=gfx1100 time=2024-07-22T13:23:30.273Z level=INFO source=amd_linux.go:301 msg="amdgpu is supported" gpu=2 gpu_type=gfx1100 time=2024-07-22T13:23:30.273Z level=INFO source=amd_linux.go:233 msg="unsupported Radeon iGPU detected skipping" id=3 total="512.0 MiB" time=2024-07-22T13:23:30.493Z level=INFO source=memory.go:133 msg="offload to gpu" layers.requested=-1 layers.real=19 memory.available="24.0 GiB" memory.required.full="37.6 GiB" memory.required.partial="23.7 GiB" memory.required.kv="256.0 MiB" memory.weights.total="35.6 GiB" memory.weights.repeating="35.5 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="184.0 MiB" memory.graph.partial="935.0 MiB" time=2024-07-22T13:23:30.494Z level=INFO source=memory.go:133 msg="offload to gpu" layers.requested=-1 layers.real=19 memory.available="24.0 GiB" memory.required.full="37.6 GiB" memory.required.partial="23.7 GiB" memory.required.kv="256.0 MiB" memory.weights.total="35.6 GiB" memory.weights.repeating="35.5 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="184.0 MiB" memory.graph.partial="935.0 MiB" time=2024-07-22T13:23:30.495Z level=INFO source=memory.go:133 msg="offload to gpu" layers.requested=-1 layers.real=19 memory.available="24.0 GiB" memory.required.full="37.6 GiB" memory.required.partial="23.7 GiB" memory.required.kv="256.0 MiB" memory.weights.total="35.6 GiB" memory.weights.repeating="35.5 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="184.0 MiB" memory.graph.partial="935.0 MiB" time=2024-07-22T13:23:30.496Z level=INFO source=memory.go:133 msg="offload to gpu" layers.requested=-1 layers.real=33 memory.available="71.9 GiB" memory.required.full="38.0 GiB" memory.required.partial="38.0 GiB" memory.required.kv="256.0 MiB" memory.weights.total="35.6 GiB" memory.weights.repeating="35.5 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="552.1 MiB" memory.graph.partial="2.7 GiB" time=2024-07-22T13:23:30.497Z level=INFO source=memory.go:133 msg="offload to gpu" layers.requested=-1 layers.real=33 memory.available="71.9 GiB" memory.required.full="38.0 GiB" memory.required.partial="38.0 GiB" memory.required.kv="256.0 MiB" memory.weights.total="35.6 GiB" memory.weights.repeating="35.5 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="552.1 MiB" memory.graph.partial="2.7 GiB" time=2024-07-22T13:23:30.498Z level=INFO source=server.go:341 msg="starting llama server" cmd="/tmp/ollama432537499/runners/rocm_v60002/ollama_llama_server --model /root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72 --ctx-size 2048 --batch-size 512 --embedding --log-disable --n-gpu-layers 33 --parallel 1 --port 39509" time=2024-07-22T13:23:30.498Z level=INFO source=sched.go:338 msg="loaded runners" count=1 time=2024-07-22T13:23:30.498Z level=INFO source=server.go:529 msg="waiting for llama runner to start responding" time=2024-07-22T13:23:30.498Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server error" INFO [main] build info | build=1 commit="5921b8f" tid="136304919219264" timestamp=1721654610 INFO [main] system info | n_threads=16 n_threads_batch=-1 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | " tid="136304919219264" timestamp=1721654610 total_threads=32 INFO [main] HTTP server listening | hostname="127.0.0.1" n_threads_http="31" port="39509" tid="136304919219264" timestamp=1721654610 llama_model_loader: loaded meta data with 26 key-value pairs and 995 tensors from /root/.ollama/models/blobs/sha256-a130d63aaf6f095d56914771afa0eb92ae04620ad496710957e9d650e4485b72 (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 = mistralai llama_model_loader: - kv 2: llama.context_length u32 = 32768 llama_model_loader: - kv 3: llama.embedding_length u32 = 4096 llama_model_loader: - kv 4: llama.block_count u32 = 32 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 7: llama.attention.head_count u32 = 32 llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 9: llama.expert_count u32 = 8 llama_model_loader: - kv 10: llama.expert_used_count u32 = 2 llama_model_loader: - kv 11: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 12: llama.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 13: general.file_type u32 = 18 llama_model_loader: - kv 14: tokenizer.ggml.model str = llama llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<... llama_model_loader: - kv 16: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... llama_model_loader: - kv 18: tokenizer.ggml.merges arr[str,58980] = ["▁ t", "i n", "e r", "▁ a", "h e... llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 21: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 24: tokenizer.chat_template str = {{ bos_token }}{% for message in mess... llama_model_loader: - kv 25: general.quantization_version u32 = 2 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type f16: 32 tensors llama_model_loader: - type q8_0: 64 tensors llama_model_loader: - type q6_K: 834 tensors llm_load_vocab: special tokens cache size = 259 llm_load_vocab: token to piece cache size = 0.3274 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = SPM llm_load_print_meta: n_vocab = 32000 llm_load_print_meta: n_merges = 0 llm_load_print_meta: n_ctx_train = 32768 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_layer = 32 llm_load_print_meta: n_rot = 128 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 = 8 llm_load_print_meta: n_expert_used = 2 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 = 1000000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_yarn_orig_ctx = 32768 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: model type = 8x7B llm_load_print_meta: model ftype = Q6_K llm_load_print_meta: model params = 46.70 B llm_load_print_meta: model size = 35.74 GiB (6.57 BPW) llm_load_print_meta: general.name = mistralai llm_load_print_meta: BOS token = 1 '<s>' llm_load_print_meta: EOS token = 2 '</s>' llm_load_print_meta: UNK token = 0 '<unk>' llm_load_print_meta: LF token = 13 '<0x0A>' time=2024-07-22T13:23:30.749Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server loading model" ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes ggml_cuda_init: found 3 ROCm devices: Device 0: Radeon RX 7900 XTX, compute capability 11.0, VMM: no Device 1: Radeon RX 7900 XTX, compute capability 11.0, VMM: no Device 2: Radeon RX 7900 XTX, compute capability 11.0, VMM: no llm_load_tensors: ggml ctx size = 1.67 MiB time=2024-07-22T13:23:34.710Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server not responding" llm_load_tensors: offloading 32 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 33/33 layers to GPU llm_load_tensors: ROCm0 buffer size = 12510.78 MiB llm_load_tensors: ROCm1 buffer size = 12510.78 MiB llm_load_tensors: ROCm2 buffer size = 11475.99 MiB llm_load_tensors: ROCm_Host buffer size = 102.54 MiB time=2024-07-22T13:23:35.412Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server loading model" time=2024-07-22T13:23:45.648Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server not responding" time=2024-07-22T13:23:46.518Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server loading model" llama_new_context_with_model: n_ctx = 2048 llama_new_context_with_model: n_batch = 512 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 1000000.0 llama_new_context_with_model: freq_scale = 1 time=2024-07-22T13:23:47.972Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server not responding" time=2024-07-22T13:23:48.334Z level=INFO source=server.go:567 msg="waiting for server to become available" status="llm server loading model" llama_kv_cache_init: ROCm0 KV buffer size = 88.00 MiB llama_kv_cache_init: ROCm1 KV buffer size = 88.00 MiB llama_kv_cache_init: ROCm2 KV buffer size = 80.00 MiB llama_new_context_with_model: KV self size = 256.00 MiB, K (f16): 128.00 MiB, V (f16): 128.00 MiB llama_new_context_with_model: ROCm_Host output buffer size = 0.14 MiB llama_new_context_with_model: pipeline parallelism enabled (n_copies=4) llama_new_context_with_model: ROCm0 compute buffer size = 208.01 MiB llama_new_context_with_model: ROCm1 compute buffer size = 208.01 MiB llama_new_context_with_model: ROCm2 compute buffer size = 208.02 MiB llama_new_context_with_model: ROCm_Host compute buffer size = 24.02 MiB llama_new_context_with_model: graph nodes = 1510 llama_new_context_with_model: graph splits = 4 INFO [main] model loaded | tid="136304919219264" timestamp=1721654631 time=2024-07-22T13:23:51.845Z level=INFO source=server.go:572 msg="llama runner started in 21.35 seconds" [GIN] 2024/07/22 - 13:23:51 | 200 | 21.576923759s | 127.0.0.1 | POST "/api/chat" ``` chat: ``` >>> hi ############################### >>> Send a message (/? for help) ``
GiteaMirror commented 2026-04-28 14:28:10 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 23, 2024):

This appears to be a duplicate of #5708

<!-- gh-comment-id:2245888025 --> @dhiltgen commented on GitHub (Jul 23, 2024): This appears to be a duplicate of #5708
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 amd bug
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#50161
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?