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 #9772] Ollama (python) Docker Parallel Requests not working #52902

New Issue
Closed
opened 2026-04-29 01:19:08 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-29 01:19:08 -05:00
Owner
Copy Link

Originally created by @ArsalanYounus007 on GitHub (Mar 14, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9772

What is the issue?

Hello,
Thank you for reading this. I have built an docker app and base image is used FROM ollama/ollama:0.5.7

My app calls ollama server multiple times (because 1 single prompt was too complex for small models)
But the problem that I am facing is I am unable to send concurrent calls to the server so that it may speed up my overall processing.
Below is the sample snippet of what I am trying to do...

import asyncio
from ollama import AsyncClient
import logging

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

async def async_ollama_chat(model: str, messages: list) -> dict:
    """Async version of ollama.chat."""
    client = AsyncClient()
    try:
        response = await client.chat(
            model=model,
            messages=messages
        )
        return response
    except Exception as e:
        logger.error(f"Error in async_ollama_chat: {str(e)}")
        raise

async def process_section(key: str, model: str, messages: list) -> tuple:
    """Process a single section."""
    try:
        response = await async_ollama_chat(model, messages)
        logger.info(f"Completed section: {key}")
        return key, response
    except Exception as e:
        logger.error(f"Error processing section '{key}': {str(e)}")
        return key, {}

async def main():
    # Sample configuration
    sections = {
        "section1": {
            "model": "llama2",
            "messages": [{"role": "user", "content": "Hello"}]
        },
        "section2": {
            "model": "llama2",
            "messages": [{"role": "user", "content": "World"}]
        }
    }

    # Process sections concurrently
    tasks = [process_section(key, config["model"], config["messages"]) 
            for key, config in sections.items()]
    results = await asyncio.gather(*tasks)
    
    # Print results
    for key, result in results:
        print(f"Section {key}: {'Success' if result else 'Failed'}")

if __name__ == "__main__":
    asyncio.run(main())

The problem is that the calls to the model still are sequential.

Can you please help this issue?

Relevant log output

[GIN] 2025/03/14 - 17:32:01 | 200 |  8.746444903s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2025/03/14 - 17:32:04 | 200 |  2.497799875s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2025/03/14 - 17:32:05 | 200 |  1.855538579s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2025/03/14 - 17:32:14 | 200 |  8.286862443s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2025/03/14 - 17:32:15 | 200 |  1.321989394s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2025/03/14 - 17:32:19 | 200 |  4.131923305s |       127.0.0.1 | POST     "/api/chat"

OS

Docker

GPU

Nvidia

CPU

Intel

Ollama version

0.5.7

Originally created by @ArsalanYounus007 on GitHub (Mar 14, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9772 ### What is the issue? Hello, Thank you for reading this. I have built an docker app and base image is used FROM ollama/ollama:0.5.7 My app calls ollama server multiple times (because 1 single prompt was too complex for small models) But the problem that I am facing is I am unable to send concurrent calls to the server so that it may speed up my overall processing. Below is the sample snippet of what I am trying to do... ``` import asyncio from ollama import AsyncClient import logging logging.basicConfig(level=logging.INFO) logger = logging.getLogger(__name__) async def async_ollama_chat(model: str, messages: list) -> dict: """Async version of ollama.chat.""" client = AsyncClient() try: response = await client.chat( model=model, messages=messages ) return response except Exception as e: logger.error(f"Error in async_ollama_chat: {str(e)}") raise async def process_section(key: str, model: str, messages: list) -> tuple: """Process a single section.""" try: response = await async_ollama_chat(model, messages) logger.info(f"Completed section: {key}") return key, response except Exception as e: logger.error(f"Error processing section '{key}': {str(e)}") return key, {} async def main(): # Sample configuration sections = { "section1": { "model": "llama2", "messages": [{"role": "user", "content": "Hello"}] }, "section2": { "model": "llama2", "messages": [{"role": "user", "content": "World"}] } } # Process sections concurrently tasks = [process_section(key, config["model"], config["messages"]) for key, config in sections.items()] results = await asyncio.gather(*tasks) # Print results for key, result in results: print(f"Section {key}: {'Success' if result else 'Failed'}") if __name__ == "__main__": asyncio.run(main()) ``` The problem is that the calls to the model still are sequential. Can you please help this issue? ### Relevant log output ```shell [GIN] 2025/03/14 - 17:32:01 | 200 | 8.746444903s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/03/14 - 17:32:04 | 200 | 2.497799875s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/03/14 - 17:32:05 | 200 | 1.855538579s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/03/14 - 17:32:14 | 200 | 8.286862443s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/03/14 - 17:32:15 | 200 | 1.321989394s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/03/14 - 17:32:19 | 200 | 4.131923305s | 127.0.0.1 | POST "/api/chat" ``` ### OS Docker ### GPU Nvidia ### CPU Intel ### Ollama version 0.5.7
GiteaMirror added the bug label 2026-04-29 01:19:08 -05:00
GiteaMirror commented 2026-04-29 01:19:17 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 14, 2025):

Have you set OLLAMA_NUM_PARALLEL in the docker environment?

<!-- gh-comment-id:2725551839 --> @rick-github commented on GitHub (Mar 14, 2025): Have you set [`OLLAMA_NUM_PARALLEL`](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-does-ollama-handle-concurrent-requests) in the docker environment?
GiteaMirror commented 2026-04-29 01:19:19 -05:00
Author
Owner
Copy Link

@ArsalanYounus007 commented on GitHub (Mar 14, 2025):

My bad, I did not provide this information.
Below is my start.sh file that starts the Ollama server

#!/bin/sh

OLLAMA_NUM_PARALLEL=10 OLLAMA_KEEP_ALIVE=-1 OLLAMA_MAX_LOADED_MODELS=3 OLLAMA_FLASH_ATTENTION=true ollama serve &
sleep 10

echo "Pulling qwen2.5:32b model..."
ollama pull qwen2.5:32b

if [ $1 = "flask" ]
then
  echo Starting Flask App...
  exec gunicorn --workers 1 --bind 0.0.0.0:5000 --timeout 600 flask_app:app
else
  echo Starting QWorker App...
  exec python3 /app/workerapp.py
fi

I have tried multiple numbers for each parameter for testing, Getting as low as 2 parallel requests

As for Hardware information, I have A100 80GB that I am using.
And it's using around 25GBs (it increases with OLLAMA_NUM_PARALLEL parameter)

<!-- gh-comment-id:2725560667 --> @ArsalanYounus007 commented on GitHub (Mar 14, 2025): My bad, I did not provide this information. Below is my start.sh file that starts the Ollama server ``` #!/bin/sh OLLAMA_NUM_PARALLEL=10 OLLAMA_KEEP_ALIVE=-1 OLLAMA_MAX_LOADED_MODELS=3 OLLAMA_FLASH_ATTENTION=true ollama serve & sleep 10 echo "Pulling qwen2.5:32b model..." ollama pull qwen2.5:32b if [ $1 = "flask" ] then echo Starting Flask App... exec gunicorn --workers 1 --bind 0.0.0.0:5000 --timeout 600 flask_app:app else echo Starting QWorker App... exec python3 /app/workerapp.py fi ``` I have tried multiple numbers for each parameter for testing, Getting as low as 2 parallel requests As for Hardware information, I have A100 80GB that I am using. And it's using around 25GBs (it increases with OLLAMA_NUM_PARALLEL parameter)
GiteaMirror commented 2026-04-29 01:19:22 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 14, 2025):

Logs may show useful info.

<!-- gh-comment-id:2725567862 --> @rick-github commented on GitHub (Mar 14, 2025): Logs may show useful info.
GiteaMirror commented 2026-04-29 01:19:23 -05:00
Author
Owner
Copy Link

@ArsalanYounus007 commented on GitHub (Mar 14, 2025):

2025/03/14 17:31:26 routes.go:1187: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:3 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:10 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-03-14T17:31:26.787Z level=INFO source=images.go:432 msg="total blobs: 15"
time=2025-03-14T17:31:26.787Z level=INFO source=images.go:439 msg="total unused blobs removed: 0"
[GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached.

[GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.
 - using env:   export GIN_MODE=release
 - using code:  gin.SetMode(gin.ReleaseMode)

[GIN-debug] POST   /api/pull                 --> github.com/ollama/ollama/server.(*Server).PullHandler-fm (5 handlers)
[GIN-debug] POST   /api/generate             --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (5 handlers)
[GIN-debug] POST   /api/chat                 --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (5 handlers)
[GIN-debug] POST   /api/embed                --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (5 handlers)
[GIN-debug] POST   /api/embeddings           --> github.com/ollama/ollama/server.(*Server).EmbeddingsHandler-fm (5 handlers)
[GIN-debug] POST   /api/create               --> github.com/ollama/ollama/server.(*Server).CreateHandler-fm (5 handlers)
[GIN-debug] POST   /api/push                 --> github.com/ollama/ollama/server.(*Server).PushHandler-fm (5 handlers)
[GIN-debug] POST   /api/copy                 --> github.com/ollama/ollama/server.(*Server).CopyHandler-fm (5 handlers)
[GIN-debug] DELETE /api/delete               --> github.com/ollama/ollama/server.(*Server).DeleteHandler-fm (5 handlers)
[GIN-debug] POST   /api/show                 --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (5 handlers)
[GIN-debug] POST   /api/blobs/:digest        --> github.com/ollama/ollama/server.(*Server).CreateBlobHandler-fm (5 handlers)
[GIN-debug] HEAD   /api/blobs/:digest        --> github.com/ollama/ollama/server.(*Server).HeadBlobHandler-fm (5 handlers)
[GIN-debug] GET    /api/ps                   --> github.com/ollama/ollama/server.(*Server).PsHandler-fm (5 handlers)
[GIN-debug] POST   /v1/chat/completions      --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (6 handlers)
[GIN-debug] POST   /v1/completions           --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (6 handlers)
[GIN-debug] POST   /v1/embeddings            --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (6 handlers)
[GIN-debug] GET    /v1/models                --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (6 handlers)
[GIN-debug] GET    /v1/models/:model         --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (6 handlers)
[GIN-debug] GET    /                         --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers)
[GIN-debug] GET    /api/tags                 --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers)
[GIN-debug] GET    /api/version              --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers)
[GIN-debug] HEAD   /                         --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers)
[GIN-debug] HEAD   /api/tags                 --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers)
[GIN-debug] HEAD   /api/version              --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers)
time=2025-03-14T17:31:26.788Z level=INFO source=routes.go:1238 msg="Listening on [::]:11434 (version 0.5.7-0-ga420a45-dirty)"
time=2025-03-14T17:31:26.788Z level=INFO source=routes.go:1267 msg="Dynamic LLM libraries" runners="[cpu_avx2 cuda_v11_avx cuda_v12_avx cpu cpu_avx]"
time=2025-03-14T17:31:26.788Z level=INFO source=gpu.go:226 msg="looking for compatible GPUs"
time=2025-03-14T17:31:27.034Z level=INFO source=types.go:131 msg="inference compute" id=GPU-24f8473e-66ad-d978-7e3f-adbc1e47307c library=cuda variant=v12 compute=8.9 driver=12.2 name="NVIDIA GeForce RTX 4090" total="23.6 GiB" available="23.2 GiB"
time=2025-03-14T17:31:27.034Z level=INFO source=types.go:131 msg="inference compute" id=GPU-de45fd91-4db6-056b-b493-d5f349d7d6a0 library=cuda variant=v12 compute=8.0 driver=12.2 name="NVIDIA A100 80GB PCIe" total="79.2 GiB" available="78.7 GiB"
Pulling qwen2.5:32b model...
[GIN] 2025/03/14 - 17:31:36 | 200 |      65.023µs |       127.0.0.1 | HEAD     "/"
time=2025-03-14T17:31:53.259Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-eabc98a9bcbfce7fd70f3e07de599f8fda98120fefed5881934161ede8bd1a41 gpu=GPU-de45fd91-4db6-056b-b493-d5f349d7d6a0 parallel=10 available=84530102272 required="25.5 GiB"
time=2025-03-14T17:31:53.467Z level=INFO source=server.go:104 msg="system memory" total="125.6 GiB" free="120.8 GiB" free_swap="2.0 GiB"
time=2025-03-14T17:31:53.672Z level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=65 layers.offload=65 layers.split="" memory.available="[78.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="25.5 GiB" memory.required.partial="25.5 GiB" memory.required.kv="5.0 GiB" memory.required.allocations="[25.5 GiB]" memory.weights.total="22.5 GiB" memory.weights.repeating="21.9 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="1.6 GiB" memory.graph.partial="2.0 GiB"
time=2025-03-14T17:31:53.672Z level=INFO source=server.go:223 msg="enabling flash attention"
time=2025-03-14T17:31:53.672Z level=WARN source=server.go:231 msg="kv cache type not supported by model" type=""
time=2025-03-14T17:31:53.672Z level=INFO source=server.go:376 msg="starting llama server" cmd="/usr/lib/ollama/runners/cuda_v12_avx/ollama_llama_server runner --model /root/.ollama/models/blobs/sha256-eabc98a9bcbfce7fd70f3e07de599f8fda98120fefed5881934161ede8bd1a41 --ctx-size 20480 --batch-size 512 --n-gpu-layers 65 --threads 8 --flash-attn --parallel 10 --port 34939"
time=2025-03-14T17:31:53.673Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2025-03-14T17:31:53.673Z level=INFO source=server.go:555 msg="waiting for llama runner to start responding"
time=2025-03-14T17:31:53.673Z level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server error"
time=2025-03-14T17:31:53.693Z level=INFO source=runner.go:936 msg="starting go runner"
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: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes
time=2025-03-14T17:31:53.706Z level=INFO source=runner.go:937 msg=system info="CUDA : ARCHS = 600,610,620,700,720,750,800,860,870,890,900 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | LLAMAFILE = 1 | AARCH64_REPACK = 1 | cgo(gcc)" threads=8
time=2025-03-14T17:31:53.706Z level=INFO source=.:0 msg="Server listening on 127.0.0.1:34939"
llama_load_model_from_file: using device CUDA0 (NVIDIA A100 80GB PCIe) - 80614 MiB free
llama_model_loader: loaded meta data with 34 key-value pairs and 771 tensors from /root/.ollama/models/blobs/sha256-eabc98a9bcbfce7fd70f3e07de599f8fda98120fefed5881934161ede8bd1a41 (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              = qwen2
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen2.5 32B Instruct
llama_model_loader: - kv   3:                           general.finetune str              = Instruct
llama_model_loader: - kv   4:                           general.basename str              = Qwen2.5
llama_model_loader: - kv   5:                         general.size_label str              = 32B
llama_model_loader: - kv   6:                            general.license str              = apache-2.0
llama_model_loader: - kv   7:                       general.license.link str              = https://huggingface.co/Qwen/Qwen2.5-3...
llama_model_loader: - kv   8:                   general.base_model.count u32              = 1
llama_model_loader: - kv   9:                  general.base_model.0.name str              = Qwen2.5 32B
llama_model_loader: - kv  10:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv  11:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2.5-32B
llama_model_loader: - kv  12:                               general.tags arr[str,2]       = ["chat", "text-generation"]
llama_model_loader: - kv  13:                          general.languages arr[str,1]       = ["en"]
llama_model_loader: - kv  14:                          qwen2.block_count u32              = 64
llama_model_loader: - kv  15:                       qwen2.context_length u32              = 32768
llama_model_loader: - kv  16:                     qwen2.embedding_length u32              = 5120
llama_model_loader: - kv  17:                  qwen2.feed_forward_length u32              = 27648
llama_model_loader: - kv  18:                 qwen2.attention.head_count u32              = 40
llama_model_loader: - kv  19:              qwen2.attention.head_count_kv u32              = 8
llama_model_loader: - kv  20:                       qwen2.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  21:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  22:                          general.file_type u32              = 15
llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  28:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  29:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  30:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  31:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  32:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  33:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  321 tensors
llama_model_loader: - type q4_K:  385 tensors
llama_model_loader: - type q6_K:   65 tensors
time=2025-03-14T17:31:53.924Z level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server loading model"
llm_load_vocab: special tokens cache size = 22
llm_load_vocab: token to piece cache size = 0.9310 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = qwen2
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 152064
llm_load_print_meta: n_merges         = 151387
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 32768
llm_load_print_meta: n_embd           = 5120
llm_load_print_meta: n_layer          = 64
llm_load_print_meta: n_head           = 40
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            = 5
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-06
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             = 27648
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        = 2
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: ssm_dt_b_c_rms   = 0
llm_load_print_meta: model type       = 32B
llm_load_print_meta: model ftype      = Q4_K - Medium
llm_load_print_meta: model params     = 32.76 B
llm_load_print_meta: model size       = 18.48 GiB (4.85 BPW) 
llm_load_print_meta: general.name     = Qwen2.5 32B Instruct
llm_load_print_meta: BOS token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOS token        = 151645 '<|im_end|>'
llm_load_print_meta: EOT token        = 151645 '<|im_end|>'
llm_load_print_meta: PAD token        = 151643 '<|endoftext|>'
llm_load_print_meta: LF token         = 148848 'ÄĬ'
llm_load_print_meta: FIM PRE token    = 151659 '<|fim_prefix|>'
llm_load_print_meta: FIM SUF token    = 151661 '<|fim_suffix|>'
llm_load_print_meta: FIM MID token    = 151660 '<|fim_middle|>'
llm_load_print_meta: FIM PAD token    = 151662 '<|fim_pad|>'
llm_load_print_meta: FIM REP token    = 151663 '<|repo_name|>'
llm_load_print_meta: FIM SEP token    = 151664 '<|file_sep|>'
llm_load_print_meta: EOG token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOG token        = 151645 '<|im_end|>'
llm_load_print_meta: EOG token        = 151662 '<|fim_pad|>'
llm_load_print_meta: EOG token        = 151663 '<|repo_name|>'
llm_load_print_meta: EOG token        = 151664 '<|file_sep|>'
llm_load_print_meta: max token length = 256
llm_load_tensors: offloading 64 repeating layers to GPU
llm_load_tensors: offloading output layer to GPU
llm_load_tensors: offloaded 65/65 layers to GPU
llm_load_tensors:   CPU_Mapped model buffer size =   417.66 MiB
llm_load_tensors:        CUDA0 model buffer size = 18508.35 MiB
llama_new_context_with_model: n_seq_max     = 10
llama_new_context_with_model: n_ctx         = 20480
llama_new_context_with_model: n_ctx_per_seq = 2048
llama_new_context_with_model: n_batch       = 5120
llama_new_context_with_model: n_ubatch      = 512
llama_new_context_with_model: flash_attn    = 1
llama_new_context_with_model: freq_base     = 1000000.0
llama_new_context_with_model: freq_scale    = 1
llama_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (32768) -- the full capacity of the model will not be utilized
llama_kv_cache_init: kv_size = 20480, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 64, can_shift = 1
llama_kv_cache_init:      CUDA0 KV buffer size =  5120.00 MiB
llama_new_context_with_model: KV self size  = 5120.00 MiB, K (f16): 2560.00 MiB, V (f16): 2560.00 MiB
llama_new_context_with_model:  CUDA_Host  output buffer size =     6.00 MiB
llama_new_context_with_model:      CUDA0 compute buffer size =   307.00 MiB
llama_new_context_with_model:  CUDA_Host compute buffer size =    50.01 MiB
llama_new_context_with_model: graph nodes  = 1991
llama_new_context_with_model: graph splits = 2
time=2025-03-14T17:31:57.690Z level=INFO source=server.go:594 msg="llama runner started in 4.02 seconds"
llama_model_loader: loaded meta data with 34 key-value pairs and 771 tensors from /root/.ollama/models/blobs/sha256-eabc98a9bcbfce7fd70f3e07de599f8fda98120fefed5881934161ede8bd1a41 (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              = qwen2
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen2.5 32B Instruct
llama_model_loader: - kv   3:                           general.finetune str              = Instruct
llama_model_loader: - kv   4:                           general.basename str              = Qwen2.5
llama_model_loader: - kv   5:                         general.size_label str              = 32B
llama_model_loader: - kv   6:                            general.license str              = apache-2.0
llama_model_loader: - kv   7:                       general.license.link str              = https://huggingface.co/Qwen/Qwen2.5-3...
llama_model_loader: - kv   8:                   general.base_model.count u32              = 1
llama_model_loader: - kv   9:                  general.base_model.0.name str              = Qwen2.5 32B
llama_model_loader: - kv  10:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv  11:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2.5-32B
llama_model_loader: - kv  12:                               general.tags arr[str,2]       = ["chat", "text-generation"]
llama_model_loader: - kv  13:                          general.languages arr[str,1]       = ["en"]
llama_model_loader: - kv  14:                          qwen2.block_count u32              = 64
llama_model_loader: - kv  15:                       qwen2.context_length u32              = 32768
llama_model_loader: - kv  16:                     qwen2.embedding_length u32              = 5120
llama_model_loader: - kv  17:                  qwen2.feed_forward_length u32              = 27648
llama_model_loader: - kv  18:                 qwen2.attention.head_count u32              = 40
llama_model_loader: - kv  19:              qwen2.attention.head_count_kv u32              = 8
llama_model_loader: - kv  20:                       qwen2.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  21:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  22:                          general.file_type u32              = 15
llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  28:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  29:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  30:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  31:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  32:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  33:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  321 tensors
llama_model_loader: - type q4_K:  385 tensors
llama_model_loader: - type q6_K:   65 tensors
llm_load_vocab: special tokens cache size = 22
llm_load_vocab: token to piece cache size = 0.9310 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = qwen2
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 152064
llm_load_print_meta: n_merges         = 151387
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     = 32.76 B
llm_load_print_meta: model size       = 18.48 GiB (4.85 BPW) 
llm_load_print_meta: general.name     = Qwen2.5 32B Instruct
llm_load_print_meta: BOS token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOS token        = 151645 '<|im_end|>'
llm_load_print_meta: EOT token        = 151645 '<|im_end|>'
llm_load_print_meta: PAD token        = 151643 '<|endoftext|>'
llm_load_print_meta: LF token         = 148848 'ÄĬ'
llm_load_print_meta: FIM PRE token    = 151659 '<|fim_prefix|>'
llm_load_print_meta: FIM SUF token    = 151661 '<|fim_suffix|>'
llm_load_print_meta: FIM MID token    = 151660 '<|fim_middle|>'
llm_load_print_meta: FIM PAD token    = 151662 '<|fim_pad|>'
llm_load_print_meta: FIM REP token    = 151663 '<|repo_name|>'
llm_load_print_meta: FIM SEP token    = 151664 '<|file_sep|>'
llm_load_print_meta: EOG token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOG token        = 151645 '<|im_end|>'
llm_load_print_meta: EOG token        = 151662 '<|fim_pad|>'
llm_load_print_meta: EOG token        = 151663 '<|repo_name|>'
llm_load_print_meta: EOG token        = 151664 '<|file_sep|>'
llm_load_print_meta: max token length = 256
llama_model_load: vocab only - skipping tensors

[GIN] 2025/03/14 - 17:32:01 | 200 |  8.746444903s |       127.0.0.1 | POST     "/api/chat" 
[REDACTED]
[GIN] 2025/03/14 - 17:32:04 | 200 |  2.497799875s |       127.0.0.1 | POST     "/api/chat" 
[REDACTED]
[GIN] 2025/03/14 - 17:32:05 | 200 |  1.855538579s |       127.0.0.1 | POST     "/api/chat" 
[REDACTED]
[GIN] 2025/03/14 - 17:32:14 | 200 |  8.286862443s |       127.0.0.1 | POST     "/api/chat" 
[REDACTED]
[GIN] 2025/03/14 - 17:32:15 | 200 |  1.321989394s |       127.0.0.1 | POST     "/api/chat" 
[REDACTED]
[GIN] 2025/03/14 - 17:32:19 | 200 |  4.131923305s |       127.0.0.1 | POST     "/api/chat" 
[REDACTED]
<!-- gh-comment-id:2725575718 --> @ArsalanYounus007 commented on GitHub (Mar 14, 2025): ``` 2025/03/14 17:31:26 routes.go:1187: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:3 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:10 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-03-14T17:31:26.787Z level=INFO source=images.go:432 msg="total blobs: 15" time=2025-03-14T17:31:26.787Z level=INFO source=images.go:439 msg="total unused blobs removed: 0" [GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached. [GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production. - using env: export GIN_MODE=release - using code: gin.SetMode(gin.ReleaseMode) [GIN-debug] POST /api/pull --> github.com/ollama/ollama/server.(*Server).PullHandler-fm (5 handlers) [GIN-debug] POST /api/generate --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (5 handlers) [GIN-debug] POST /api/chat --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (5 handlers) [GIN-debug] POST /api/embed --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (5 handlers) [GIN-debug] POST /api/embeddings --> github.com/ollama/ollama/server.(*Server).EmbeddingsHandler-fm (5 handlers) [GIN-debug] POST /api/create --> github.com/ollama/ollama/server.(*Server).CreateHandler-fm (5 handlers) [GIN-debug] POST /api/push --> github.com/ollama/ollama/server.(*Server).PushHandler-fm (5 handlers) [GIN-debug] POST /api/copy --> github.com/ollama/ollama/server.(*Server).CopyHandler-fm (5 handlers) [GIN-debug] DELETE /api/delete --> github.com/ollama/ollama/server.(*Server).DeleteHandler-fm (5 handlers) [GIN-debug] POST /api/show --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (5 handlers) [GIN-debug] POST /api/blobs/:digest --> github.com/ollama/ollama/server.(*Server).CreateBlobHandler-fm (5 handlers) [GIN-debug] HEAD /api/blobs/:digest --> github.com/ollama/ollama/server.(*Server).HeadBlobHandler-fm (5 handlers) [GIN-debug] GET /api/ps --> github.com/ollama/ollama/server.(*Server).PsHandler-fm (5 handlers) [GIN-debug] POST /v1/chat/completions --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (6 handlers) [GIN-debug] POST /v1/completions --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (6 handlers) [GIN-debug] POST /v1/embeddings --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (6 handlers) [GIN-debug] GET /v1/models --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (6 handlers) [GIN-debug] GET /v1/models/:model --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (6 handlers) [GIN-debug] GET / --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers) [GIN-debug] GET /api/tags --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers) [GIN-debug] GET /api/version --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers) [GIN-debug] HEAD / --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers) [GIN-debug] HEAD /api/tags --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers) [GIN-debug] HEAD /api/version --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers) time=2025-03-14T17:31:26.788Z level=INFO source=routes.go:1238 msg="Listening on [::]:11434 (version 0.5.7-0-ga420a45-dirty)" time=2025-03-14T17:31:26.788Z level=INFO source=routes.go:1267 msg="Dynamic LLM libraries" runners="[cpu_avx2 cuda_v11_avx cuda_v12_avx cpu cpu_avx]" time=2025-03-14T17:31:26.788Z level=INFO source=gpu.go:226 msg="looking for compatible GPUs" time=2025-03-14T17:31:27.034Z level=INFO source=types.go:131 msg="inference compute" id=GPU-24f8473e-66ad-d978-7e3f-adbc1e47307c library=cuda variant=v12 compute=8.9 driver=12.2 name="NVIDIA GeForce RTX 4090" total="23.6 GiB" available="23.2 GiB" time=2025-03-14T17:31:27.034Z level=INFO source=types.go:131 msg="inference compute" id=GPU-de45fd91-4db6-056b-b493-d5f349d7d6a0 library=cuda variant=v12 compute=8.0 driver=12.2 name="NVIDIA A100 80GB PCIe" total="79.2 GiB" available="78.7 GiB" Pulling qwen2.5:32b model... [GIN] 2025/03/14 - 17:31:36 | 200 | 65.023µs | 127.0.0.1 | HEAD "/" time=2025-03-14T17:31:53.259Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-eabc98a9bcbfce7fd70f3e07de599f8fda98120fefed5881934161ede8bd1a41 gpu=GPU-de45fd91-4db6-056b-b493-d5f349d7d6a0 parallel=10 available=84530102272 required="25.5 GiB" time=2025-03-14T17:31:53.467Z level=INFO source=server.go:104 msg="system memory" total="125.6 GiB" free="120.8 GiB" free_swap="2.0 GiB" time=2025-03-14T17:31:53.672Z level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=65 layers.offload=65 layers.split="" memory.available="[78.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="25.5 GiB" memory.required.partial="25.5 GiB" memory.required.kv="5.0 GiB" memory.required.allocations="[25.5 GiB]" memory.weights.total="22.5 GiB" memory.weights.repeating="21.9 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="1.6 GiB" memory.graph.partial="2.0 GiB" time=2025-03-14T17:31:53.672Z level=INFO source=server.go:223 msg="enabling flash attention" time=2025-03-14T17:31:53.672Z level=WARN source=server.go:231 msg="kv cache type not supported by model" type="" time=2025-03-14T17:31:53.672Z level=INFO source=server.go:376 msg="starting llama server" cmd="/usr/lib/ollama/runners/cuda_v12_avx/ollama_llama_server runner --model /root/.ollama/models/blobs/sha256-eabc98a9bcbfce7fd70f3e07de599f8fda98120fefed5881934161ede8bd1a41 --ctx-size 20480 --batch-size 512 --n-gpu-layers 65 --threads 8 --flash-attn --parallel 10 --port 34939" time=2025-03-14T17:31:53.673Z level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2025-03-14T17:31:53.673Z level=INFO source=server.go:555 msg="waiting for llama runner to start responding" time=2025-03-14T17:31:53.673Z level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server error" time=2025-03-14T17:31:53.693Z level=INFO source=runner.go:936 msg="starting go runner" 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: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes time=2025-03-14T17:31:53.706Z level=INFO source=runner.go:937 msg=system info="CUDA : ARCHS = 600,610,620,700,720,750,800,860,870,890,900 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | LLAMAFILE = 1 | AARCH64_REPACK = 1 | cgo(gcc)" threads=8 time=2025-03-14T17:31:53.706Z level=INFO source=.:0 msg="Server listening on 127.0.0.1:34939" llama_load_model_from_file: using device CUDA0 (NVIDIA A100 80GB PCIe) - 80614 MiB free llama_model_loader: loaded meta data with 34 key-value pairs and 771 tensors from /root/.ollama/models/blobs/sha256-eabc98a9bcbfce7fd70f3e07de599f8fda98120fefed5881934161ede8bd1a41 (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 = qwen2 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Qwen2.5 32B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Qwen2.5 llama_model_loader: - kv 5: general.size_label str = 32B llama_model_loader: - kv 6: general.license str = apache-2.0 llama_model_loader: - kv 7: general.license.link str = https://huggingface.co/Qwen/Qwen2.5-3... llama_model_loader: - kv 8: general.base_model.count u32 = 1 llama_model_loader: - kv 9: general.base_model.0.name str = Qwen2.5 32B llama_model_loader: - kv 10: general.base_model.0.organization str = Qwen llama_model_loader: - kv 11: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen2.5-32B llama_model_loader: - kv 12: general.tags arr[str,2] = ["chat", "text-generation"] llama_model_loader: - kv 13: general.languages arr[str,1] = ["en"] llama_model_loader: - kv 14: qwen2.block_count u32 = 64 llama_model_loader: - kv 15: qwen2.context_length u32 = 32768 llama_model_loader: - kv 16: qwen2.embedding_length u32 = 5120 llama_model_loader: - kv 17: qwen2.feed_forward_length u32 = 27648 llama_model_loader: - kv 18: qwen2.attention.head_count u32 = 40 llama_model_loader: - kv 19: qwen2.attention.head_count_kv u32 = 8 llama_model_loader: - kv 20: qwen2.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 21: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 22: general.file_type u32 = 15 llama_model_loader: - kv 23: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 24: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 26: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 27: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 28: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 29: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 30: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 31: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 32: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 33: general.quantization_version u32 = 2 llama_model_loader: - type f32: 321 tensors llama_model_loader: - type q4_K: 385 tensors llama_model_loader: - type q6_K: 65 tensors time=2025-03-14T17:31:53.924Z level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server loading model" llm_load_vocab: special tokens cache size = 22 llm_load_vocab: token to piece cache size = 0.9310 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = qwen2 llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 152064 llm_load_print_meta: n_merges = 151387 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 32768 llm_load_print_meta: n_embd = 5120 llm_load_print_meta: n_layer = 64 llm_load_print_meta: n_head = 40 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 = 5 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-06 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 = 27648 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 = 2 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: ssm_dt_b_c_rms = 0 llm_load_print_meta: model type = 32B llm_load_print_meta: model ftype = Q4_K - Medium llm_load_print_meta: model params = 32.76 B llm_load_print_meta: model size = 18.48 GiB (4.85 BPW) llm_load_print_meta: general.name = Qwen2.5 32B Instruct llm_load_print_meta: BOS token = 151643 '<|endoftext|>' llm_load_print_meta: EOS token = 151645 '<|im_end|>' llm_load_print_meta: EOT token = 151645 '<|im_end|>' llm_load_print_meta: PAD token = 151643 '<|endoftext|>' llm_load_print_meta: LF token = 148848 'ÄĬ' llm_load_print_meta: FIM PRE token = 151659 '<|fim_prefix|>' llm_load_print_meta: FIM SUF token = 151661 '<|fim_suffix|>' llm_load_print_meta: FIM MID token = 151660 '<|fim_middle|>' llm_load_print_meta: FIM PAD token = 151662 '<|fim_pad|>' llm_load_print_meta: FIM REP token = 151663 '<|repo_name|>' llm_load_print_meta: FIM SEP token = 151664 '<|file_sep|>' llm_load_print_meta: EOG token = 151643 '<|endoftext|>' llm_load_print_meta: EOG token = 151645 '<|im_end|>' llm_load_print_meta: EOG token = 151662 '<|fim_pad|>' llm_load_print_meta: EOG token = 151663 '<|repo_name|>' llm_load_print_meta: EOG token = 151664 '<|file_sep|>' llm_load_print_meta: max token length = 256 llm_load_tensors: offloading 64 repeating layers to GPU llm_load_tensors: offloading output layer to GPU llm_load_tensors: offloaded 65/65 layers to GPU llm_load_tensors: CPU_Mapped model buffer size = 417.66 MiB llm_load_tensors: CUDA0 model buffer size = 18508.35 MiB llama_new_context_with_model: n_seq_max = 10 llama_new_context_with_model: n_ctx = 20480 llama_new_context_with_model: n_ctx_per_seq = 2048 llama_new_context_with_model: n_batch = 5120 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 1 llama_new_context_with_model: freq_base = 1000000.0 llama_new_context_with_model: freq_scale = 1 llama_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (32768) -- the full capacity of the model will not be utilized llama_kv_cache_init: kv_size = 20480, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 64, can_shift = 1 llama_kv_cache_init: CUDA0 KV buffer size = 5120.00 MiB llama_new_context_with_model: KV self size = 5120.00 MiB, K (f16): 2560.00 MiB, V (f16): 2560.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 6.00 MiB llama_new_context_with_model: CUDA0 compute buffer size = 307.00 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 50.01 MiB llama_new_context_with_model: graph nodes = 1991 llama_new_context_with_model: graph splits = 2 time=2025-03-14T17:31:57.690Z level=INFO source=server.go:594 msg="llama runner started in 4.02 seconds" llama_model_loader: loaded meta data with 34 key-value pairs and 771 tensors from /root/.ollama/models/blobs/sha256-eabc98a9bcbfce7fd70f3e07de599f8fda98120fefed5881934161ede8bd1a41 (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 = qwen2 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Qwen2.5 32B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Qwen2.5 llama_model_loader: - kv 5: general.size_label str = 32B llama_model_loader: - kv 6: general.license str = apache-2.0 llama_model_loader: - kv 7: general.license.link str = https://huggingface.co/Qwen/Qwen2.5-3... llama_model_loader: - kv 8: general.base_model.count u32 = 1 llama_model_loader: - kv 9: general.base_model.0.name str = Qwen2.5 32B llama_model_loader: - kv 10: general.base_model.0.organization str = Qwen llama_model_loader: - kv 11: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen2.5-32B llama_model_loader: - kv 12: general.tags arr[str,2] = ["chat", "text-generation"] llama_model_loader: - kv 13: general.languages arr[str,1] = ["en"] llama_model_loader: - kv 14: qwen2.block_count u32 = 64 llama_model_loader: - kv 15: qwen2.context_length u32 = 32768 llama_model_loader: - kv 16: qwen2.embedding_length u32 = 5120 llama_model_loader: - kv 17: qwen2.feed_forward_length u32 = 27648 llama_model_loader: - kv 18: qwen2.attention.head_count u32 = 40 llama_model_loader: - kv 19: qwen2.attention.head_count_kv u32 = 8 llama_model_loader: - kv 20: qwen2.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 21: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 22: general.file_type u32 = 15 llama_model_loader: - kv 23: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 24: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 26: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 27: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 28: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 29: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 30: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 31: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 32: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 33: general.quantization_version u32 = 2 llama_model_loader: - type f32: 321 tensors llama_model_loader: - type q4_K: 385 tensors llama_model_loader: - type q6_K: 65 tensors llm_load_vocab: special tokens cache size = 22 llm_load_vocab: token to piece cache size = 0.9310 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = qwen2 llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 152064 llm_load_print_meta: n_merges = 151387 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 = 32.76 B llm_load_print_meta: model size = 18.48 GiB (4.85 BPW) llm_load_print_meta: general.name = Qwen2.5 32B Instruct llm_load_print_meta: BOS token = 151643 '<|endoftext|>' llm_load_print_meta: EOS token = 151645 '<|im_end|>' llm_load_print_meta: EOT token = 151645 '<|im_end|>' llm_load_print_meta: PAD token = 151643 '<|endoftext|>' llm_load_print_meta: LF token = 148848 'ÄĬ' llm_load_print_meta: FIM PRE token = 151659 '<|fim_prefix|>' llm_load_print_meta: FIM SUF token = 151661 '<|fim_suffix|>' llm_load_print_meta: FIM MID token = 151660 '<|fim_middle|>' llm_load_print_meta: FIM PAD token = 151662 '<|fim_pad|>' llm_load_print_meta: FIM REP token = 151663 '<|repo_name|>' llm_load_print_meta: FIM SEP token = 151664 '<|file_sep|>' llm_load_print_meta: EOG token = 151643 '<|endoftext|>' llm_load_print_meta: EOG token = 151645 '<|im_end|>' llm_load_print_meta: EOG token = 151662 '<|fim_pad|>' llm_load_print_meta: EOG token = 151663 '<|repo_name|>' llm_load_print_meta: EOG token = 151664 '<|file_sep|>' llm_load_print_meta: max token length = 256 llama_model_load: vocab only - skipping tensors [GIN] 2025/03/14 - 17:32:01 | 200 | 8.746444903s | 127.0.0.1 | POST "/api/chat" [REDACTED] [GIN] 2025/03/14 - 17:32:04 | 200 | 2.497799875s | 127.0.0.1 | POST "/api/chat" [REDACTED] [GIN] 2025/03/14 - 17:32:05 | 200 | 1.855538579s | 127.0.0.1 | POST "/api/chat" [REDACTED] [GIN] 2025/03/14 - 17:32:14 | 200 | 8.286862443s | 127.0.0.1 | POST "/api/chat" [REDACTED] [GIN] 2025/03/14 - 17:32:15 | 200 | 1.321989394s | 127.0.0.1 | POST "/api/chat" [REDACTED] [GIN] 2025/03/14 - 17:32:19 | 200 | 4.131923305s | 127.0.0.1 | POST "/api/chat" [REDACTED] ```
GiteaMirror commented 2026-04-29 01:19:25 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 14, 2025):

Nothing unusual in the log. How sure are you that the tasks are sequential? I modified your test script to do both async and sync runs and the async takes less time.

--- 9772.py.orig        2025-03-14 20:51:56.897747355 +0100
+++ 9772.py     2025-03-14 21:34:49.317201739 +0100
@@ -1,6 +1,9 @@
+#!/usr/bin/env python3
+
 import asyncio
 from ollama import AsyncClient
 import logging
+import time
 
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
@@ -40,11 +43,18 @@
             "messages": [{"role": "user", "content": "World"}]
         }
     }
+    sections = {f"section{i}":{"model":"llama3.2","messages":[{"role":"user","content":"count to 100"}]} for i in range(10)}
 
     # Process sections concurrently
+    t0 = time.perf_counter()
     tasks = [process_section(key, config["model"], config["messages"]) 
             for key, config in sections.items()]
     results = await asyncio.gather(*tasks)
+    t1 = time.perf_counter()
+    for key, config in sections.items():
+      await process_section(key, config["model"], config["messages"])
+    t2 = time.perf_counter()
+    print(f"async: {t1-t0}, sync: {t2-t1}")
     
     # Print results
     for key, result in results:

$ ./9772.py
INFO:httpx:HTTP Request: POST http://127.0.0.1:11434/api/chat "HTTP/1.1 200 OK"
INFO:__main__:Completed section: section5
...
INFO:__main__:Completed section: section9
async: 5.778746280993801, sync: 25.40941732400097
<!-- gh-comment-id:2725711839 --> @rick-github commented on GitHub (Mar 14, 2025): Nothing unusual in the log. How sure are you that the tasks are sequential? I modified your test script to do both async and sync runs and the async takes less time. ```diff --- 9772.py.orig 2025-03-14 20:51:56.897747355 +0100 +++ 9772.py 2025-03-14 21:34:49.317201739 +0100 @@ -1,6 +1,9 @@ +#!/usr/bin/env python3 + import asyncio from ollama import AsyncClient import logging +import time logging.basicConfig(level=logging.INFO) logger = logging.getLogger(__name__) @@ -40,11 +43,18 @@ "messages": [{"role": "user", "content": "World"}] } } + sections = {f"section{i}":{"model":"llama3.2","messages":[{"role":"user","content":"count to 100"}]} for i in range(10)} # Process sections concurrently + t0 = time.perf_counter() tasks = [process_section(key, config["model"], config["messages"]) for key, config in sections.items()] results = await asyncio.gather(*tasks) + t1 = time.perf_counter() + for key, config in sections.items(): + await process_section(key, config["model"], config["messages"]) + t2 = time.perf_counter() + print(f"async: {t1-t0}, sync: {t2-t1}") # Print results for key, result in results: ``` ```console $ ./9772.py INFO:httpx:HTTP Request: POST http://127.0.0.1:11434/api/chat "HTTP/1.1 200 OK" INFO:__main__:Completed section: section5 ... INFO:__main__:Completed section: section9 async: 5.778746280993801, sync: 25.40941732400097 ```
GiteaMirror commented 2026-04-29 01:19:26 -05:00
Author
Owner
Copy Link

@ArsalanYounus007 commented on GitHub (Mar 17, 2025):

Can you please tell me the Ollama version that you are using?
Maybe something is off with the version that I am using

<!-- gh-comment-id:2730532971 --> @ArsalanYounus007 commented on GitHub (Mar 17, 2025): Can you please tell me the Ollama version that you are using? Maybe something is off with the version that I am using
GiteaMirror commented 2026-04-29 01:19:27 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 17, 2025):

0.5.7

<!-- gh-comment-id:2730649850 --> @rick-github commented on GitHub (Mar 17, 2025): 0.5.7
GiteaMirror commented 2026-04-29 01:19:28 -05:00
Author
Owner
Copy Link

@ArsalanYounus007 commented on GitHub (Mar 18, 2025):

I got it working with some changes in my code, Closing this one
Thank you!!

<!-- gh-comment-id:2732540767 --> @ArsalanYounus007 commented on GitHub (Mar 18, 2025): I got it working with some changes in my code, Closing this one Thank you!!
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#52902
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?