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 #6337] Why is the occupancy of my Llama 3 model not high when using the GPU NV T2000, but instead it is computing using the CPU? #3977

New Issue
Closed
opened 2026-04-12 14:50:54 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-12 14:50:54 -05:00
Owner
Copy Link

Originally created by @pewjs on GitHub (Aug 13, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6337

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

When I use Ollama with Llama 3 or any other model, I find that the GPU usage is constantly fluctuating at high and low levels and is not fully occupied. However, the CPU usage is still approximately 40% high. Various parameters have been enabled but to no avail.
image
[GIN] 2024/08/13 - 18:11:47 | 200 | 5.2344ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2024/08/13 - 18:11:47 | 200 | 0s | 127.0.0.1 | GET "/api/version"
time=2024-08-13T18:12:10.197+08:00 level=DEBUG source=gpu.go:362 msg="updating system memory data" before.total="63.7 GiB" before.free="42.7 GiB" before.free_swap="40.3 GiB" now.total="63.7 GiB" now.free="42.4 GiB" now.free_swap="39.9 GiB"
time=2024-08-13T18:12:10.210+08:00 level=DEBUG source=gpu.go:410 msg="updating cuda memory data" gpu=GPU-84808663-ce4d-0d38-31a7-655311eef7b0 name="Quadro T2000" overhead="275.7 MiB" before.total="4.0 GiB" before.free="3.2 GiB" now.total="4.0 GiB" now.free="3.3 GiB" now.used="490.9 MiB"
time=2024-08-13T18:12:10.246+08:00 level=DEBUG source=sched.go:219 msg="loading first model" model=D:\ollama\blobs\sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa
time=2024-08-13T18:12:10.246+08:00 level=DEBUG source=memory.go:101 msg=evaluating library=cuda gpu_count=1 available="[3.3 GiB]"
time=2024-08-13T18:12:10.247+08:00 level=DEBUG source=server.go:101 msg="system memory" total="63.7 GiB" free="42.4 GiB" free_swap="39.9 GiB"
time=2024-08-13T18:12:10.247+08:00 level=DEBUG source=memory.go:101 msg=evaluating library=cuda gpu_count=1 available="[3.3 GiB]"
time=2024-08-13T18:12:10.248+08:00 level=INFO source=memory.go:309 msg="offload to cuda" layers.requested=-1 layers.model=33 layers.offload=12 layers.split="" memory.available="[3.3 GiB]" memory.required.full="6.6 GiB" memory.required.partial="3.1 GiB" memory.required.kv="1.2 GiB" memory.required.allocations="[3.1 GiB]" memory.weights.total="4.9 GiB" memory.weights.repeating="4.5 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="692.0 MiB" memory.graph.partial="725.0 MiB"
time=2024-08-13T18:12:10.252+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cpu\ollama_llama_server.exe
time=2024-08-13T18:12:10.252+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cpu_avx\ollama_llama_server.exe
time=2024-08-13T18:12:10.252+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cpu_avx2\ollama_llama_server.exe
time=2024-08-13T18:12:10.252+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cuda_v11.3\ollama_llama_server.exe
time=2024-08-13T18:12:10.252+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\rocm_v6.1\ollama_llama_server.exe
time=2024-08-13T18:12:10.258+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cpu\ollama_llama_server.exe
time=2024-08-13T18:12:10.258+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cpu_avx\ollama_llama_server.exe
time=2024-08-13T18:12:10.258+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cpu_avx2\ollama_llama_server.exe
time=2024-08-13T18:12:10.258+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cuda_v11.3\ollama_llama_server.exe
time=2024-08-13T18:12:10.258+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\rocm_v6.1\ollama_llama_server.exe
time=2024-08-13T18:12:10.310+08:00 level=INFO source=server.go:393 msg="starting llama server" cmd="C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cuda_v11.3\ollama_llama_server.exe --model D:\ollama\blobs\sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa --ctx-size 10240 --batch-size 512 --embedding --log-disable --n-gpu-layers 12 --verbose --no-mmap --parallel 1 --port 1498"
time=2024-08-13T18:12:10.310+08:00 level=DEBUG source=server.go:410 msg=subprocess environment="[CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6 CUDA_PATH_V12_3=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.3 CUDA_PATH_V12_6=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6 PATH=C:\Users\pewjs\AppData\Local\Programs\Ollama\cuda;C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cuda_v11.3;C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners;C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6\bin;C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6\libnvvp;C:\Program Files\Common Files\Oracle\Java\javapath;C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.3\bin;C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.3\libnvvp;D:\anaconda3;D:\anaconda3\Scripts;C:\Python27;C:\Python27\Scripts;C:\Program Files\ImageMagick-7.1.1-Q16-HDRI;C:\Program Files (x86)\VMware\VMware Workstation\bin\;C:\Program Files\Java\jdk1.8.0_281\bin;C:\Program Files\Java\jdk1.8.0_281\jre\bin;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0\;C:\WINDOWS\System32\OpenSSH\;C:\Program Files (x86)\Windows Kits\8.1\Windows Performance Toolkit\;C:\Program Files\OpenVPN\bin;C:\Program Files\nodejs\;C:\Program Files\dotnet\;C:\Users\pewjs\AppData\Local\Google\Chrome\Application;C:\Program Files\Git\cmd;C:\Program Files (x86)\PuTTY\;C:\Program Files\Bandizip\;C:\Users\pewjs\AppData\Roaming\FreeControl\scrcpy-win64-v2.1.1\;C:\Users\pewjs\AppData\Roaming\FreeControl\scrcpy-win64-v2.3.1\;C:\Program Files\010 Editor;D:\PHP\;C:\Program Files (x86)\NVIDIA Corporation\PhysX\Common;C:\Program Files\Docker\Docker\resources\bin;C:\Program Files\CMake\bin;D:\anaconda3\Library\bin;D:\anaconda3\Library\mingw-w64\bin;c:\;C:\MinGW\bin;;C:\Program Files\NVIDIA Corporation\NVIDIA NvDLISR;C:\Program Files\NVIDIA Corporation\Nsight Compute 2024.3.0\;C:\Users\pewjs\AppData\Local\Programs\Python\Launcher\;C:\Users\pewjs\AppData\Local\Microsoft\WindowsApps;C:\Program Files (x86)\Fiddler2;d:\Program Files (x86)\Fiddler2;C:\Users\pewjs\AppData\Local\Microsoft\WindowsApps;C:\Program Files (x86)\Nmap;C:\Users\pewjs\AppData\Roaming\npm;C:\Users\pewjs\AppData\Local\Programs\Microsoft VS Code\bin;C:\Program Files\JetBrains\IntelliJ IDEA 2023.3.1\bin;;C:\Program Files\JetBrains\PyCharm 2023.3.2\bin;;;C:\Users\pewjs\AppData\Local\Programs\Ollama;C:\Users\pewjs\AppData\Local\Programs\retoolkit\network\nmap;C:\Users\pewjs\AppData\Local\Programs\retoolkit\bin;C:\Users\pewjs\AppData\Local\Programs\retoolkit\android\dex2jar;C:\Users\pewjs\AppData\Local\Programs\retoolkit\debuggers\hyperdbg;C:\Users\pewjs\AppData\Local\Programs\retoolkit\dotnet\de4dot;C:\Users\pewjs\AppData\Local\Programs\retoolkit\ole\lessmsi;C:\Users\pewjs\AppData\Local\Programs\retoolkit\ole\officemalscanner;C:\Users\pewjs\AppData\Local\Programs\retoolkit\processinspection\hollowshunter;C:\Users\pewjs\AppData\Local\Programs\retoolkit\processinspection\observer;C:\Users\pewjs\AppData\Local\Programs\retoolkit\processinspection\pesieve;C:\Users\pewjs\AppData\Local\Programs\retoolkit\programming\winpython\python-3.11.3.amd64;C:\Users\pewjs\AppData\Local\Programs\retoolkit\utilities\winapiexec CUDA_VISIBLE_DEVICES=GPU-84808663-ce4d-0d38-31a7-655311eef7b0]"
time=2024-08-13T18:12:10.340+08:00 level=INFO source=sched.go:445 msg="loaded runners" count=1
time=2024-08-13T18:12:10.340+08:00 level=INFO source=server.go:593 msg="waiting for llama runner to start responding"
time=2024-08-13T18:12:10.341+08:00 level=INFO source=server.go:627 msg="waiting for server to become available" status="llm server error"
INFO [wmain] build info | build=3535 commit="1e6f6554" tid="3064" timestamp=1723543930
INFO [wmain] system info | n_threads=6 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="3064" timestamp=1723543930 total_threads=12
INFO [wmain] HTTP server listening | hostname="127.0.0.1" n_threads_http="11" port="1498" tid="3064" timestamp=1723543930
llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from D:\ollama\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=2024-08-13T18:12:10.603+08:00 level=INFO source=server.go:627 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: 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: LF token = 128 'Ä'
llm_load_print_meta: EOT token = 128009 '<|eot_id|>'
llm_load_print_meta: max token length = 256
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: Quadro T2000, compute capability 7.5, VMM: yes
llm_load_tensors: ggml ctx size = 0.27 MiB
llm_load_tensors: offloading 12 repeating layers to GPU
llm_load_tensors: offloaded 12/33 layers to GPU
llm_load_tensors: CUDA_Host buffer size = 3033.43 MiB
llm_load_tensors: CUDA0 buffer size = 1404.38 MiB
time=2024-08-13T18:12:12.705+08:00 level=DEBUG source=server.go:638 msg="model load progress 0.06"
time=2024-08-13T18:12:12.983+08:00 level=DEBUG source=server.go:638 msg="model load progress 0.30"
time=2024-08-13T18:12:13.249+08:00 level=DEBUG source=server.go:638 msg="model load progress 0.48"
time=2024-08-13T18:12:13.527+08:00 level=DEBUG source=server.go:638 msg="model load progress 0.70"
time=2024-08-13T18:12:13.780+08:00 level=DEBUG source=server.go:638 msg="model load progress 0.86"
llama_new_context_with_model: n_ctx = 10240
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 = 500000.0
llama_new_context_with_model: freq_scale = 1
time=2024-08-13T18:12:14.060+08:00 level=DEBUG source=server.go:638 msg="model load progress 1.00"
llama_kv_cache_init: CUDA_Host KV buffer size = 800.00 MiB
llama_kv_cache_init: CUDA0 KV buffer size = 480.00 MiB
llama_new_context_with_model: KV self size = 1280.00 MiB, K (f16): 640.00 MiB, V (f16): 640.00 MiB
llama_new_context_with_model: CUDA_Host output buffer size = 0.50 MiB
llama_new_context_with_model: CUDA0 compute buffer size = 725.00 MiB
llama_new_context_with_model: CUDA_Host compute buffer size = 28.01 MiB
llama_new_context_with_model: graph nodes = 1030
llama_new_context_with_model: graph splits = 224
time=2024-08-13T18:12:14.341+08:00 level=DEBUG source=server.go:641 msg="model load completed, waiting for server to become available" status="llm server loading model"
DEBUG [initialize] initializing slots | n_slots=1 tid="3064" timestamp=1723543936
DEBUG [initialize] new slot | n_ctx_slot=10240 slot_id=0 tid="3064" timestamp=1723543936
INFO [wmain] model loaded | tid="3064" timestamp=1723543936
DEBUG [update_slots] all slots are idle and system prompt is empty, clear the KV cache | tid="3064" timestamp=1723543936
DEBUG [process_single_task] slot data | n_idle_slots=1 n_processing_slots=0 task_id=0 tid="3064" timestamp=1723543936
time=2024-08-13T18:12:16.233+08:00 level=INFO source=server.go:632 msg="llama runner started in 5.89 seconds"
time=2024-08-13T18:12:16.233+08:00 level=DEBUG source=sched.go:458 msg="finished setting up runner" model=D:\ollama\blobs\sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa
time=2024-08-13T18:12:16.233+08:00 level=DEBUG source=routes.go:1361 msg="chat request" images=0 prompt="<|start_header_id|>user<|end_header_id|>\n\n介绍一下大模型的学习方法500字<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
DEBUG [process_single_task] slot data | n_idle_slots=1 n_processing_slots=0 task_id=1 tid="3064" timestamp=1723543936
DEBUG [launch_slot_with_data] slot is processing task | slot_id=0 task_id=2 tid="3064" timestamp=1723543936
DEBUG [update_slots] slot progression | ga_i=0 n_past=0 n_past_se=0 n_prompt_tokens_processed=19 slot_id=0 task_id=2 tid="3064" timestamp=1723543936
DEBUG [update_slots] kv cache rm [p0, end) | p0=0 slot_id=0 task_id=2 tid="3064" timestamp=1723543936

PS C:\WINDOWS\system32> nvidia-smi -q -d POWER,TEMPERATURE,PERFORMANCE

==============NVSMI LOG==============

Timestamp : Tue Aug 13 18:17:20 2024
Driver Version : 560.76
CUDA Version : 12.6

Attached GPUs : 1
GPU 00000000:01:00.0
Performance State : P0
Clocks Event Reasons
Idle : Active
Applications Clocks Setting : Not Active
SW Power Cap : Not Active
HW Slowdown : Not Active
HW Thermal Slowdown : Not Active
HW Power Brake Slowdown : Not Active
Sync Boost : Not Active
SW Thermal Slowdown : Not Active
Display Clock Setting : Not Active
Sparse Operation Mode : N/A
Temperature
GPU Current Temp : 65 C
GPU T.Limit Temp : N/A
GPU Shutdown Temp : 98 C
GPU Slowdown Temp : 93 C
GPU Max Operating Temp : 102 C
GPU Target Temperature : 75 C
Memory Current Temp : N/A
Memory Max Operating Temp : N/A
GPU Power Readings
Power Draw : 14.14 W
Current Power Limit : 30.00 W
Requested Power Limit : 35.00 W
Default Power Limit : 35.00 W
Min Power Limit : 1.00 W
Max Power Limit : 35.00 W
Power Samples
Duration : Not Found
Number of Samples : Not Found
Max : Not Found
Min : Not Found
Avg : Not Found
GPU Memory Power Readings
Power Draw : N/A
Module Power Readings
Power Draw : N/A
Current Power Limit : N/A
Requested Power Limit : N/A
Default Power Limit : N/A
Min Power Limit : N/A
Max Power Limit : N/A

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.1.35

Originally created by @pewjs on GitHub (Aug 13, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6337 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? When I use Ollama with Llama 3 or any other model, I find that the GPU usage is constantly fluctuating at high and low levels and is not fully occupied. However, the CPU usage is still approximately 40% high. Various parameters have been enabled but to no avail. ![image](https://github.com/user-attachments/assets/76ff4660-f8e1-4344-b4df-4783e73d22ac) [GIN] 2024/08/13 - 18:11:47 | 200 | 5.2344ms | 127.0.0.1 | GET "/api/tags" [GIN] 2024/08/13 - 18:11:47 | 200 | 0s | 127.0.0.1 | GET "/api/version" time=2024-08-13T18:12:10.197+08:00 level=DEBUG source=gpu.go:362 msg="updating system memory data" before.total="63.7 GiB" before.free="42.7 GiB" before.free_swap="40.3 GiB" now.total="63.7 GiB" now.free="42.4 GiB" now.free_swap="39.9 GiB" time=2024-08-13T18:12:10.210+08:00 level=DEBUG source=gpu.go:410 msg="updating cuda memory data" gpu=GPU-84808663-ce4d-0d38-31a7-655311eef7b0 name="Quadro T2000" overhead="275.7 MiB" before.total="4.0 GiB" before.free="3.2 GiB" now.total="4.0 GiB" now.free="3.3 GiB" now.used="490.9 MiB" time=2024-08-13T18:12:10.246+08:00 level=DEBUG source=sched.go:219 msg="loading first model" model=D:\ollama\blobs\sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa time=2024-08-13T18:12:10.246+08:00 level=DEBUG source=memory.go:101 msg=evaluating library=cuda gpu_count=1 available="[3.3 GiB]" time=2024-08-13T18:12:10.247+08:00 level=DEBUG source=server.go:101 msg="system memory" total="63.7 GiB" free="42.4 GiB" free_swap="39.9 GiB" time=2024-08-13T18:12:10.247+08:00 level=DEBUG source=memory.go:101 msg=evaluating library=cuda gpu_count=1 available="[3.3 GiB]" time=2024-08-13T18:12:10.248+08:00 level=INFO source=memory.go:309 msg="offload to cuda" layers.requested=-1 layers.model=33 layers.offload=12 layers.split="" memory.available="[3.3 GiB]" memory.required.full="6.6 GiB" memory.required.partial="3.1 GiB" memory.required.kv="1.2 GiB" memory.required.allocations="[3.1 GiB]" memory.weights.total="4.9 GiB" memory.weights.repeating="4.5 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="692.0 MiB" memory.graph.partial="725.0 MiB" time=2024-08-13T18:12:10.252+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cpu\ollama_llama_server.exe time=2024-08-13T18:12:10.252+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cpu_avx\ollama_llama_server.exe time=2024-08-13T18:12:10.252+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cpu_avx2\ollama_llama_server.exe time=2024-08-13T18:12:10.252+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cuda_v11.3\ollama_llama_server.exe time=2024-08-13T18:12:10.252+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\rocm_v6.1\ollama_llama_server.exe time=2024-08-13T18:12:10.258+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cpu\ollama_llama_server.exe time=2024-08-13T18:12:10.258+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cpu_avx\ollama_llama_server.exe time=2024-08-13T18:12:10.258+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cpu_avx2\ollama_llama_server.exe time=2024-08-13T18:12:10.258+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cuda_v11.3\ollama_llama_server.exe time=2024-08-13T18:12:10.258+08:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\rocm_v6.1\ollama_llama_server.exe time=2024-08-13T18:12:10.310+08:00 level=INFO source=server.go:393 msg="starting llama server" cmd="C:\\Users\\pewjs\\AppData\\Local\\Programs\\Ollama\\ollama_runners\\cuda_v11.3\\ollama_llama_server.exe --model D:\\ollama\\blobs\\sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa --ctx-size 10240 --batch-size 512 --embedding --log-disable --n-gpu-layers 12 --verbose --no-mmap --parallel 1 --port 1498" time=2024-08-13T18:12:10.310+08:00 level=DEBUG source=server.go:410 msg=subprocess environment="[CUDA_PATH=C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v12.6 CUDA_PATH_V12_3=C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v12.3 CUDA_PATH_V12_6=C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v12.6 PATH=C:\\Users\\pewjs\\AppData\\Local\\Programs\\Ollama\\cuda;C:\\Users\\pewjs\\AppData\\Local\\Programs\\Ollama\\ollama_runners\\cuda_v11.3;C:\\Users\\pewjs\\AppData\\Local\\Programs\\Ollama\\ollama_runners;C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v12.6\\bin;C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v12.6\\libnvvp;C:\\Program Files\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v12.3\\bin;C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v12.3\\libnvvp;D:\\anaconda3;D:\\anaconda3\\Scripts;C:\\Python27;C:\\Python27\\Scripts;C:\\Program Files\\ImageMagick-7.1.1-Q16-HDRI;C:\\Program Files (x86)\\VMware\\VMware Workstation\\bin\\;C:\\Program Files\\Java\\jdk1.8.0_281\\bin;C:\\Program Files\\Java\\jdk1.8.0_281\\jre\\bin;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files (x86)\\Windows Kits\\8.1\\Windows Performance Toolkit\\;C:\\Program Files\\OpenVPN\\bin;C:\\Program Files\\nodejs\\;C:\\Program Files\\dotnet\\;C:\\Users\\pewjs\\AppData\\Local\\Google\\Chrome\\Application;C:\\Program Files\\Git\\cmd;C:\\Program Files (x86)\\PuTTY\\;C:\\Program Files\\Bandizip\\;C:\\Users\\pewjs\\AppData\\Roaming\\FreeControl\\scrcpy-win64-v2.1.1\\;C:\\Users\\pewjs\\AppData\\Roaming\\FreeControl\\scrcpy-win64-v2.3.1\\;C:\\Program Files\\010 Editor;D:\\PHP\\;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files\\CMake\\bin;D:\\anaconda3\\Library\\bin;D:\\anaconda3\\Library\\mingw-w64\\bin;c:\\;C:\\MinGW\\bin;;C:\\Program Files\\NVIDIA Corporation\\NVIDIA NvDLISR;C:\\Program Files\\NVIDIA Corporation\\Nsight Compute 2024.3.0\\;C:\\Users\\pewjs\\AppData\\Local\\Programs\\Python\\Launcher\\;C:\\Users\\pewjs\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Program Files (x86)\\Fiddler2;d:\\Program Files (x86)\\Fiddler2;C:\\Users\\pewjs\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Program Files (x86)\\Nmap;C:\\Users\\pewjs\\AppData\\Roaming\\npm;C:\\Users\\pewjs\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Program Files\\JetBrains\\IntelliJ IDEA 2023.3.1\\bin;;C:\\Program Files\\JetBrains\\PyCharm 2023.3.2\\bin;;;C:\\Users\\pewjs\\AppData\\Local\\Programs\\Ollama;C:\\Users\\pewjs\\AppData\\Local\\Programs\\retoolkit\\network\\nmap;C:\\Users\\pewjs\\AppData\\Local\\Programs\\retoolkit\\bin;C:\\Users\\pewjs\\AppData\\Local\\Programs\\retoolkit\\android\\dex2jar;C:\\Users\\pewjs\\AppData\\Local\\Programs\\retoolkit\\debuggers\\hyperdbg;C:\\Users\\pewjs\\AppData\\Local\\Programs\\retoolkit\\dotnet\\de4dot;C:\\Users\\pewjs\\AppData\\Local\\Programs\\retoolkit\\ole\\lessmsi;C:\\Users\\pewjs\\AppData\\Local\\Programs\\retoolkit\\ole\\officemalscanner;C:\\Users\\pewjs\\AppData\\Local\\Programs\\retoolkit\\processinspection\\hollowshunter;C:\\Users\\pewjs\\AppData\\Local\\Programs\\retoolkit\\processinspection\\observer;C:\\Users\\pewjs\\AppData\\Local\\Programs\\retoolkit\\processinspection\\pesieve;C:\\Users\\pewjs\\AppData\\Local\\Programs\\retoolkit\\programming\\winpython\\python-3.11.3.amd64;C:\\Users\\pewjs\\AppData\\Local\\Programs\\retoolkit\\utilities\\winapiexec CUDA_VISIBLE_DEVICES=GPU-84808663-ce4d-0d38-31a7-655311eef7b0]" time=2024-08-13T18:12:10.340+08:00 level=INFO source=sched.go:445 msg="loaded runners" count=1 time=2024-08-13T18:12:10.340+08:00 level=INFO source=server.go:593 msg="waiting for llama runner to start responding" time=2024-08-13T18:12:10.341+08:00 level=INFO source=server.go:627 msg="waiting for server to become available" status="llm server error" INFO [wmain] build info | build=3535 commit="1e6f6554" tid="3064" timestamp=1723543930 INFO [wmain] system info | n_threads=6 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="3064" timestamp=1723543930 total_threads=12 INFO [wmain] HTTP server listening | hostname="127.0.0.1" n_threads_http="11" port="1498" tid="3064" timestamp=1723543930 llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from D:\ollama\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=2024-08-13T18:12:10.603+08:00 level=INFO source=server.go:627 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: 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: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_print_meta: max token length = 256 ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: Quadro T2000, compute capability 7.5, VMM: yes llm_load_tensors: ggml ctx size = 0.27 MiB llm_load_tensors: offloading 12 repeating layers to GPU llm_load_tensors: offloaded 12/33 layers to GPU llm_load_tensors: CUDA_Host buffer size = 3033.43 MiB llm_load_tensors: CUDA0 buffer size = 1404.38 MiB time=2024-08-13T18:12:12.705+08:00 level=DEBUG source=server.go:638 msg="model load progress 0.06" time=2024-08-13T18:12:12.983+08:00 level=DEBUG source=server.go:638 msg="model load progress 0.30" time=2024-08-13T18:12:13.249+08:00 level=DEBUG source=server.go:638 msg="model load progress 0.48" time=2024-08-13T18:12:13.527+08:00 level=DEBUG source=server.go:638 msg="model load progress 0.70" time=2024-08-13T18:12:13.780+08:00 level=DEBUG source=server.go:638 msg="model load progress 0.86" llama_new_context_with_model: n_ctx = 10240 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 = 500000.0 llama_new_context_with_model: freq_scale = 1 time=2024-08-13T18:12:14.060+08:00 level=DEBUG source=server.go:638 msg="model load progress 1.00" llama_kv_cache_init: CUDA_Host KV buffer size = 800.00 MiB llama_kv_cache_init: CUDA0 KV buffer size = 480.00 MiB llama_new_context_with_model: KV self size = 1280.00 MiB, K (f16): 640.00 MiB, V (f16): 640.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 0.50 MiB llama_new_context_with_model: CUDA0 compute buffer size = 725.00 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 28.01 MiB llama_new_context_with_model: graph nodes = 1030 llama_new_context_with_model: graph splits = 224 time=2024-08-13T18:12:14.341+08:00 level=DEBUG source=server.go:641 msg="model load completed, waiting for server to become available" status="llm server loading model" DEBUG [initialize] initializing slots | n_slots=1 tid="3064" timestamp=1723543936 DEBUG [initialize] new slot | n_ctx_slot=10240 slot_id=0 tid="3064" timestamp=1723543936 INFO [wmain] model loaded | tid="3064" timestamp=1723543936 DEBUG [update_slots] all slots are idle and system prompt is empty, clear the KV cache | tid="3064" timestamp=1723543936 DEBUG [process_single_task] slot data | n_idle_slots=1 n_processing_slots=0 task_id=0 tid="3064" timestamp=1723543936 time=2024-08-13T18:12:16.233+08:00 level=INFO source=server.go:632 msg="llama runner started in 5.89 seconds" time=2024-08-13T18:12:16.233+08:00 level=DEBUG source=sched.go:458 msg="finished setting up runner" model=D:\ollama\blobs\sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa time=2024-08-13T18:12:16.233+08:00 level=DEBUG source=routes.go:1361 msg="chat request" images=0 prompt="<|start_header_id|>user<|end_header_id|>\n\n介绍一下大模型的学习方法500字<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n" DEBUG [process_single_task] slot data | n_idle_slots=1 n_processing_slots=0 task_id=1 tid="3064" timestamp=1723543936 DEBUG [launch_slot_with_data] slot is processing task | slot_id=0 task_id=2 tid="3064" timestamp=1723543936 DEBUG [update_slots] slot progression | ga_i=0 n_past=0 n_past_se=0 n_prompt_tokens_processed=19 slot_id=0 task_id=2 tid="3064" timestamp=1723543936 DEBUG [update_slots] kv cache rm [p0, end) | p0=0 slot_id=0 task_id=2 tid="3064" timestamp=1723543936 PS C:\WINDOWS\system32> nvidia-smi -q -d POWER,TEMPERATURE,PERFORMANCE ==============NVSMI LOG============== Timestamp : Tue Aug 13 18:17:20 2024 Driver Version : 560.76 CUDA Version : 12.6 Attached GPUs : 1 GPU 00000000:01:00.0 Performance State : P0 Clocks Event Reasons Idle : Active Applications Clocks Setting : Not Active SW Power Cap : Not Active HW Slowdown : Not Active HW Thermal Slowdown : Not Active HW Power Brake Slowdown : Not Active Sync Boost : Not Active SW Thermal Slowdown : Not Active Display Clock Setting : Not Active Sparse Operation Mode : N/A Temperature GPU Current Temp : 65 C GPU T.Limit Temp : N/A GPU Shutdown Temp : 98 C GPU Slowdown Temp : 93 C GPU Max Operating Temp : 102 C GPU Target Temperature : 75 C Memory Current Temp : N/A Memory Max Operating Temp : N/A GPU Power Readings Power Draw : 14.14 W Current Power Limit : 30.00 W Requested Power Limit : 35.00 W Default Power Limit : 35.00 W Min Power Limit : 1.00 W Max Power Limit : 35.00 W Power Samples Duration : Not Found Number of Samples : Not Found Max : Not Found Min : Not Found Avg : Not Found GPU Memory Power Readings Power Draw : N/A Module Power Readings Power Draw : N/A Current Power Limit : N/A Requested Power Limit : N/A Default Power Limit : N/A Min Power Limit : N/A Max Power Limit : N/A ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.35
GiteaMirror added the questionperformancenvidia labels 2026-04-12 14:50:54 -05:00
GiteaMirror commented 2026-04-12 14:50:55 -05:00
Author
Owner
Copy Link

@Cephra commented on GitHub (Aug 13, 2024):

I see that you're using Ollama 0.1.35.
Can you try using the latest version?

<!-- gh-comment-id:2286216570 --> @Cephra commented on GitHub (Aug 13, 2024): I see that you're using Ollama 0.1.35. Can you try using the latest version?
GiteaMirror commented 2026-04-12 14:50:56 -05:00
Author
Owner
Copy Link

@pewjs commented on GitHub (Aug 14, 2024):

image
I have upgraded to 0.1.36, but the result is still the same. The GPU is fluctuating, the CPU occupancy is 43%, and the output is lagging.

<!-- gh-comment-id:2287594806 --> @pewjs commented on GitHub (Aug 14, 2024): ![image](https://github.com/user-attachments/assets/f7abd021-589d-4f91-b75e-8794d18e181e) I have upgraded to 0.1.36, but the result is still the same. The GPU is fluctuating, the CPU occupancy is 43%, and the output is lagging.
GiteaMirror commented 2026-04-12 14:50:56 -05:00
Author
Owner
Copy Link

@pewjs commented on GitHub (Aug 14, 2024):

2024/08/14 09:07:52 routes.go:1125: 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:2m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:D:\ollama 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:C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-08-14T09:07:52.497+08:00 level=INFO source=images.go:782 msg="total blobs: 22"
time=2024-08-14T09:07:52.498+08:00 level=INFO source=images.go:790 msg="total unused blobs removed: 0"
time=2024-08-14T09:07:52.501+08:00 level=INFO source=routes.go:1172 msg="Listening on [::]:11434 (version 0.3.6)"
time=2024-08-14T09:07:52.506+08:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu_avx2 cuda_v11.3 rocm_v6.1 cpu cpu_avx]"
time=2024-08-14T09:07:52.507+08:00 level=INFO source=gpu.go:204 msg="looking for compatible GPUs"
time=2024-08-14T09:07:53.771+08:00 level=INFO source=gpu.go:288 msg="detected OS VRAM overhead" id=GPU-84808663-ce4d-0d38-31a7-655311eef7b0 library=cuda compute=7.5 driver=12.6 name="Quadro T2000" overhead="642.2 MiB"
time=2024-08-14T09:07:53.781+08:00 level=INFO source=types.go:105 msg="inference compute" id=GPU-84808663-ce4d-0d38-31a7-655311eef7b0 library=cuda compute=7.5 driver=12.6 name="Quadro T2000" total="4.0 GiB" available="3.2 GiB"
[GIN] 2024/08/14 - 09:08:07 | 200 | 543.9µs | 127.0.0.1 | GET "/api/version"
[GIN] 2024/08/14 - 09:08:17 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2024/08/14 - 09:08:17 | 200 | 31.9696ms | 127.0.0.1 | POST "/api/show"
time=2024-08-14T09:08:17.692+08:00 level=INFO source=memory.go:309 msg="offload to cuda" layers.requested=-1 layers.model=33 layers.offload=16 layers.split="" memory.available="[3.2 GiB]" memory.required.full="5.5 GiB" memory.required.partial="3.2 GiB" memory.required.kv="256.0 MiB" memory.required.allocations="[3.2 GiB]" memory.weights.total="3.9 GiB" memory.weights.repeating="3.5 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="164.0 MiB" memory.graph.partial="677.5 MiB"
time=2024-08-14T09:08:17.740+08:00 level=INFO source=server.go:393 msg="starting llama server" cmd="C:\Users\pewjs\AppData\Local\Programs\Ollama\ollama_runners\cuda_v11.3\ollama_llama_server.exe --model D:\ollama\blobs\sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa --ctx-size 2048 --batch-size 512 --embedding --log-disable --n-gpu-layers 16 --no-mmap --parallel 1 --port 50987"
time=2024-08-14T09:08:17.836+08:00 level=INFO source=sched.go:445 msg="loaded runners" count=1
time=2024-08-14T09:08:17.836+08:00 level=INFO source=server.go:593 msg="waiting for llama runner to start responding"
time=2024-08-14T09:08:17.836+08:00 level=INFO source=server.go:627 msg="waiting for server to become available" status="llm server error"
INFO [wmain] build info | build=3535 commit="1e6f6554" tid="5832" timestamp=1723597697
INFO [wmain] system info | n_threads=6 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="5832" timestamp=1723597697 total_threads=12
INFO [wmain] HTTP server listening | hostname="127.0.0.1" n_threads_http="11" port="50987" tid="5832" timestamp=1723597697
llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from D:\ollama\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=2024-08-14T09:08:18.090+08:00 level=INFO source=server.go:627 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: 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: LF token = 128 'Ä'
llm_load_print_meta: EOT token = 128009 '<|eot_id|>'
llm_load_print_meta: max token length = 256
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: Quadro T2000, compute capability 7.5, VMM: yes
llm_load_tensors: ggml ctx size = 0.27 MiB
llm_load_tensors: offloading 16 repeating layers to GPU
llm_load_tensors: offloaded 16/33 layers to GPU
llm_load_tensors: CUDA_Host buffer size = 2565.30 MiB
llm_load_tensors: CUDA0 buffer size = 1872.50 MiB
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 = 500000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: CUDA_Host KV buffer size = 128.00 MiB
llama_kv_cache_init: CUDA0 KV buffer size = 128.00 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: CUDA_Host output buffer size = 0.50 MiB
llama_new_context_with_model: CUDA0 compute buffer size = 677.48 MiB
llama_new_context_with_model: CUDA_Host compute buffer size = 12.01 MiB
llama_new_context_with_model: graph nodes = 1030
llama_new_context_with_model: graph splits = 180
INFO [wmain] model loaded | tid="5832" timestamp=1723597704
time=2024-08-14T09:08:24.579+08:00 level=INFO source=server.go:632 msg="llama runner started in 6.74 seconds"
[GIN] 2024/08/14 - 09:08:24 | 200 | 6.9495504s | 127.0.0.1 | POST "/api/chat"
[GIN] 2024/08/14 - 09:12:01 | 200 | 3m17s | 127.0.0.1 | POST "/api/chat"

<!-- gh-comment-id:2287605672 --> @pewjs commented on GitHub (Aug 14, 2024): 2024/08/14 09:07:52 routes.go:1125: 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:2m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:D:\\ollama 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:C:\\Users\\pewjs\\AppData\\Local\\Programs\\Ollama\\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-08-14T09:07:52.497+08:00 level=INFO source=images.go:782 msg="total blobs: 22" time=2024-08-14T09:07:52.498+08:00 level=INFO source=images.go:790 msg="total unused blobs removed: 0" time=2024-08-14T09:07:52.501+08:00 level=INFO source=routes.go:1172 msg="Listening on [::]:11434 (version 0.3.6)" time=2024-08-14T09:07:52.506+08:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu_avx2 cuda_v11.3 rocm_v6.1 cpu cpu_avx]" time=2024-08-14T09:07:52.507+08:00 level=INFO source=gpu.go:204 msg="looking for compatible GPUs" time=2024-08-14T09:07:53.771+08:00 level=INFO source=gpu.go:288 msg="detected OS VRAM overhead" id=GPU-84808663-ce4d-0d38-31a7-655311eef7b0 library=cuda compute=7.5 driver=12.6 name="Quadro T2000" overhead="642.2 MiB" time=2024-08-14T09:07:53.781+08:00 level=INFO source=types.go:105 msg="inference compute" id=GPU-84808663-ce4d-0d38-31a7-655311eef7b0 library=cuda compute=7.5 driver=12.6 name="Quadro T2000" total="4.0 GiB" available="3.2 GiB" [GIN] 2024/08/14 - 09:08:07 | 200 | 543.9µs | 127.0.0.1 | GET "/api/version" [GIN] 2024/08/14 - 09:08:17 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2024/08/14 - 09:08:17 | 200 | 31.9696ms | 127.0.0.1 | POST "/api/show" time=2024-08-14T09:08:17.692+08:00 level=INFO source=memory.go:309 msg="offload to cuda" layers.requested=-1 layers.model=33 layers.offload=16 layers.split="" memory.available="[3.2 GiB]" memory.required.full="5.5 GiB" memory.required.partial="3.2 GiB" memory.required.kv="256.0 MiB" memory.required.allocations="[3.2 GiB]" memory.weights.total="3.9 GiB" memory.weights.repeating="3.5 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="164.0 MiB" memory.graph.partial="677.5 MiB" time=2024-08-14T09:08:17.740+08:00 level=INFO source=server.go:393 msg="starting llama server" cmd="C:\\Users\\pewjs\\AppData\\Local\\Programs\\Ollama\\ollama_runners\\cuda_v11.3\\ollama_llama_server.exe --model D:\\ollama\\blobs\\sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa --ctx-size 2048 --batch-size 512 --embedding --log-disable --n-gpu-layers 16 --no-mmap --parallel 1 --port 50987" time=2024-08-14T09:08:17.836+08:00 level=INFO source=sched.go:445 msg="loaded runners" count=1 time=2024-08-14T09:08:17.836+08:00 level=INFO source=server.go:593 msg="waiting for llama runner to start responding" time=2024-08-14T09:08:17.836+08:00 level=INFO source=server.go:627 msg="waiting for server to become available" status="llm server error" INFO [wmain] build info | build=3535 commit="1e6f6554" tid="5832" timestamp=1723597697 INFO [wmain] system info | n_threads=6 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="5832" timestamp=1723597697 total_threads=12 INFO [wmain] HTTP server listening | hostname="127.0.0.1" n_threads_http="11" port="50987" tid="5832" timestamp=1723597697 llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from D:\ollama\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=2024-08-14T09:08:18.090+08:00 level=INFO source=server.go:627 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: 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: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_print_meta: max token length = 256 ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: Quadro T2000, compute capability 7.5, VMM: yes llm_load_tensors: ggml ctx size = 0.27 MiB llm_load_tensors: offloading 16 repeating layers to GPU llm_load_tensors: offloaded 16/33 layers to GPU llm_load_tensors: CUDA_Host buffer size = 2565.30 MiB llm_load_tensors: CUDA0 buffer size = 1872.50 MiB 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 = 500000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CUDA_Host KV buffer size = 128.00 MiB llama_kv_cache_init: CUDA0 KV buffer size = 128.00 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: CUDA_Host output buffer size = 0.50 MiB llama_new_context_with_model: CUDA0 compute buffer size = 677.48 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 12.01 MiB llama_new_context_with_model: graph nodes = 1030 llama_new_context_with_model: graph splits = 180 INFO [wmain] model loaded | tid="5832" timestamp=1723597704 time=2024-08-14T09:08:24.579+08:00 level=INFO source=server.go:632 msg="llama runner started in 6.74 seconds" [GIN] 2024/08/14 - 09:08:24 | 200 | 6.9495504s | 127.0.0.1 | POST "/api/chat" [GIN] 2024/08/14 - 09:12:01 | 200 | 3m17s | 127.0.0.1 | POST "/api/chat"
GiteaMirror commented 2026-04-12 14:50:57 -05:00
Author
Owner
Copy Link

@Cephra commented on GitHub (Aug 14, 2024):

latest is v0.3.6

<!-- gh-comment-id:2288486695 --> @Cephra commented on GitHub (Aug 14, 2024): latest is v0.3.6
GiteaMirror commented 2026-04-12 14:50:57 -05:00
Author
Owner
Copy Link

@pewjs commented on GitHub (Aug 15, 2024):

sorry,I made a writing mistake. My version is v0.3.6

<!-- gh-comment-id:2290797535 --> @pewjs commented on GitHub (Aug 15, 2024): sorry,I made a writing mistake. My version is v0.3.6
GiteaMirror commented 2026-04-12 14:50:57 -05:00
Author
Owner
Copy Link

@Cephra commented on GitHub (Aug 15, 2024):

But you still experience the same error?

<!-- gh-comment-id:2291294872 --> @Cephra commented on GitHub (Aug 15, 2024): But you still experience the same error?
GiteaMirror commented 2026-04-12 14:50:58 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Sep 5, 2024):

From what I can see in the logs, I don't believe there's a bug here. You have a 4G GPU with ~3.3G available. You're trying to load a model which requires ~6.6G, so it's being split between GPU and CPU. When this happens, the CPU is typically much slower than the GPU, and results in the GPU spending much of it's time waiting for the CPU to catch up. If you load a smaller model, you should see higher GPU utilization, and higher token rate. You can also use the ollama ps command to see the loaded model and how much is on CPU vs. GPU.

<!-- gh-comment-id:2332695787 --> @dhiltgen commented on GitHub (Sep 5, 2024): From what I can see in the logs, I don't believe there's a bug here. You have a 4G GPU with ~3.3G available. You're trying to load a model which requires ~6.6G, so it's being split between GPU and CPU. When this happens, the CPU is typically much slower than the GPU, and results in the GPU spending much of it's time waiting for the CPU to catch up. If you load a smaller model, you should see higher GPU utilization, and higher token rate. You can also use the `ollama ps` command to see the loaded model and how much is on CPU vs. GPU.
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 nvidia performance question
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#3977
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?