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 #9264] 无法加载所有GPU #6038

New Issue
Closed
opened 2026-04-12 17:22:27 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 17:22:27 -05:00
Owner
Copy Link

Originally created by @sunt1009 on GitHub (Feb 21, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9264

What is the issue?

操作系统为4个A40显卡，显存大小：48G/个，目前运行任务为：DeepSeek-R1:70b,任务在运行的过程中只有一个GPU占用率98%，其余三个GPU使用率为0%

Image

Relevant log output

1.ollama启动日志：
INFO server config env="map[CUDA_VISIBLE_DEVICES:0,1,2,3 GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY:cuda_v12 OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/data/deepseek-modules/70b OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
source=images.go:432 msg="total blobs: 5"
source=images.go:439 msg="total unused blobs removed: 0"
source=routes.go:1237 msg="Listening on [::]:11434 (version 0.5.11)"
source=gpu.go:217 msg="looking for compatible GPUs"
source=types.go:130 msg="inference compute" id=GPU-2b1e2aa8-a371-42ac-8f25-8f39c12e8707 library=cuda variant=v12 compute=8.6 driver=12.8 name="NVIDIA A40" total="44.4 GiB" available="44.1 GiB"
source=types.go:130 msg="inference compute" id=GPU-f1404a54-99bd-776c-b7c2-10f438641b38 library=cuda variant=v12 compute=8.6 driver=12.8 name="NVIDIA A40" total="44.4 GiB" available="44.2 GiB"
source=types.go:130 msg="inference compute" id=GPU-cb4c513b-6932-4aa6-181b-d49801a5f2e9 library=cuda variant=v12 compute=8.6 driver=12.8 name="NVIDIA A40" total="44.4 GiB" available="44.2 GiB"
source=types.go:130 msg="inference compute" id=GPU-475ec94b-5592-966f-dffd-557aad68f985 library=cuda variant=v12 compute=8.6 driver=12.8 name="NVIDIA A40" total="44.4 GiB" available="44.2 GiB"

2.ollama运行任务的日志
level=INFO source=server.go:596 msg="llama runner started in 8.28 seconds"
llama_model_loader: loaded meta data with 30 key-value pairs and 724 tensors from /data/deepseek-modules/70b/blobs/sha256-4cd576d9aa16961244012223abf01445567b061f1814b57dfef699e4cf8df339 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = llama
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = DeepSeek R1 Distill Llama 70B
llama_model_loader: - kv   3:                           general.basename str              = DeepSeek-R1-Distill-Llama
llama_model_loader: - kv   4:                         general.size_label str              = 70B
llama_model_loader: - kv   5:                          llama.block_count u32              = 80
llama_model_loader: - kv   6:                       llama.context_length u32              = 131072
llama_model_loader: - kv   7:                     llama.embedding_length u32              = 8192
llama_model_loader: - kv   8:                  llama.feed_forward_length u32              = 28672
llama_model_loader: - kv   9:                 llama.attention.head_count u32              = 64
llama_model_loader: - kv  10:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv  11:                       llama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv  12:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  13:                 llama.attention.key_length u32              = 128
llama_model_loader: - kv  14:               llama.attention.value_length u32              = 128
llama_model_loader: - kv  15:                          general.file_type u32              = 15
llama_model_loader: - kv  16:                           llama.vocab_size u32              = 128256
llama_model_loader: - kv  17:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  18:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  19:                         tokenizer.ggml.pre str              = llama-bpe
llama_model_loader: - kv  20:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  21:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  22:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv  23:                tokenizer.ggml.bos_token_id u32              = 128000
llama_model_loader: - kv  24:                tokenizer.ggml.eos_token_id u32              = 128001
llama_model_loader: - kv  25:            tokenizer.ggml.padding_token_id u32              = 128001
llama_model_loader: - kv  26:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  27:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  28:                    tokenizer.chat_template str              = {% if not add_generation_prompt is de...
llama_model_loader: - kv  29:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  162 tensors
llama_model_loader: - type q4_K:  441 tensors
llama_model_loader: - type q5_K:   40 tensors
llama_model_loader: - type q6_K:   81 tensors
llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
llm_load_vocab: special tokens cache size = 256
llm_load_vocab: token to piece cache size = 0.7999 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 128256
llm_load_print_meta: n_merges         = 280147
llm_load_print_meta: vocab_only       = 1
llm_load_print_meta: model type       = ?B
llm_load_print_meta: model ftype      = all F32
llm_load_print_meta: model params     = 70.55 B
llm_load_print_meta: model size       = 39.59 GiB (4.82 BPW)
llm_load_print_meta: general.name     = DeepSeek R1 Distill Llama 70B
llm_load_print_meta: BOS token        = 128000 '<｜begin▁of▁sentence｜>'
llm_load_print_meta: EOS token        = 128001 '<｜end▁of▁sentence｜>'
llm_load_print_meta: EOT token        = 128001 '<｜end▁of▁sentence｜>'
llm_load_print_meta: EOM token        = 128008 '<|eom_id|>'
llm_load_print_meta: PAD token        = 128001 '<｜end▁of▁sentence｜>'
llm_load_print_meta: LF token         = 128 'Ä'
llm_load_print_meta: EOG token        = 128001 '<｜end▁of▁sentence｜>'
llm_load_print_meta: EOG token        = 128008 '<|eom_id|>'
llm_load_print_meta: EOG token        = 128009 '<|eot_id|>'
llm_load_print_meta: max token length = 256
llama_model_load: vocab only - skipping tensors

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.5.11

Originally created by @sunt1009 on GitHub (Feb 21, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9264 ### What is the issue? 操作系统为4个A40显卡，显存大小：48G/个，目前运行任务为：DeepSeek-R1:70b,任务在运行的过程中只有一个GPU占用率98%，其余三个GPU使用率为0% ![Image](https://github.com/user-attachments/assets/15d5b458-24a3-47a9-a460-31ee2f88fb5b) ### Relevant log output ```shell 1.ollama启动日志： INFO server config env="map[CUDA_VISIBLE_DEVICES:0,1,2,3 GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY:cuda_v12 OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/data/deepseek-modules/70b OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" source=images.go:432 msg="total blobs: 5" source=images.go:439 msg="total unused blobs removed: 0" source=routes.go:1237 msg="Listening on [::]:11434 (version 0.5.11)" source=gpu.go:217 msg="looking for compatible GPUs" source=types.go:130 msg="inference compute" id=GPU-2b1e2aa8-a371-42ac-8f25-8f39c12e8707 library=cuda variant=v12 compute=8.6 driver=12.8 name="NVIDIA A40" total="44.4 GiB" available="44.1 GiB" source=types.go:130 msg="inference compute" id=GPU-f1404a54-99bd-776c-b7c2-10f438641b38 library=cuda variant=v12 compute=8.6 driver=12.8 name="NVIDIA A40" total="44.4 GiB" available="44.2 GiB" source=types.go:130 msg="inference compute" id=GPU-cb4c513b-6932-4aa6-181b-d49801a5f2e9 library=cuda variant=v12 compute=8.6 driver=12.8 name="NVIDIA A40" total="44.4 GiB" available="44.2 GiB" source=types.go:130 msg="inference compute" id=GPU-475ec94b-5592-966f-dffd-557aad68f985 library=cuda variant=v12 compute=8.6 driver=12.8 name="NVIDIA A40" total="44.4 GiB" available="44.2 GiB" 2.ollama运行任务的日志 level=INFO source=server.go:596 msg="llama runner started in 8.28 seconds" llama_model_loader: loaded meta data with 30 key-value pairs and 724 tensors from /data/deepseek-modules/70b/blobs/sha256-4cd576d9aa16961244012223abf01445567b061f1814b57dfef699e4cf8df339 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = DeepSeek R1 Distill Llama 70B llama_model_loader: - kv 3: general.basename str = DeepSeek-R1-Distill-Llama llama_model_loader: - kv 4: general.size_label str = 70B llama_model_loader: - kv 5: llama.block_count u32 = 80 llama_model_loader: - kv 6: llama.context_length u32 = 131072 llama_model_loader: - kv 7: llama.embedding_length u32 = 8192 llama_model_loader: - kv 8: llama.feed_forward_length u32 = 28672 llama_model_loader: - kv 9: llama.attention.head_count u32 = 64 llama_model_loader: - kv 10: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 11: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 12: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 13: llama.attention.key_length u32 = 128 llama_model_loader: - kv 14: llama.attention.value_length u32 = 128 llama_model_loader: - kv 15: general.file_type u32 = 15 llama_model_loader: - kv 16: llama.vocab_size u32 = 128256 llama_model_loader: - kv 17: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 18: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 19: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 20: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 21: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 22: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 24: tokenizer.ggml.eos_token_id u32 = 128001 llama_model_loader: - kv 25: tokenizer.ggml.padding_token_id u32 = 128001 llama_model_loader: - kv 26: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 28: tokenizer.chat_template str = {% if not add_generation_prompt is de... llama_model_loader: - kv 29: general.quantization_version u32 = 2 llama_model_loader: - type f32: 162 tensors llama_model_loader: - type q4_K: 441 tensors llama_model_loader: - type q5_K: 40 tensors llama_model_loader: - type q6_K: 81 tensors llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 0.7999 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: vocab_only = 1 llm_load_print_meta: model type = ?B llm_load_print_meta: model ftype = all F32 llm_load_print_meta: model params = 70.55 B llm_load_print_meta: model size = 39.59 GiB (4.82 BPW) llm_load_print_meta: general.name = DeepSeek R1 Distill Llama 70B llm_load_print_meta: BOS token = 128000 '<｜begin▁of▁sentence｜>' llm_load_print_meta: EOS token = 128001 '<｜end▁of▁sentence｜>' llm_load_print_meta: EOT token = 128001 '<｜end▁of▁sentence｜>' llm_load_print_meta: EOM token = 128008 '<|eom_id|>' llm_load_print_meta: PAD token = 128001 '<｜end▁of▁sentence｜>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOG token = 128001 '<｜end▁of▁sentence｜>' llm_load_print_meta: EOG token = 128008 '<|eom_id|>' llm_load_print_meta: EOG token = 128009 '<|eot_id|>' llm_load_print_meta: max token length = 256 llama_model_load: vocab only - skipping tensors ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.5.11
GiteaMirror added the bug label 2026-04-12 17:22:27 -05:00
GiteaMirror commented 2026-04-12 17:22:28 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 21, 2025):

If the model fits on one GPU, only one GPU is used. There is no performance improvement by using multiple GPUs for a single completion.

<!-- gh-comment-id:2673885328 --> @rick-github commented on GitHub (Feb 21, 2025): If the model fits on one GPU, only one GPU is used. There is [no performance improvement](https://github.com/ollama/ollama/issues/7648#issuecomment-2473561990) by using multiple GPUs for a single completion.
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 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#6038
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?