[GH-ISSUE #9180] Ollama not running with ROCm backend? #31739

New Issue

GiteaMirror · 2026-04-22T12:27:48-05:00

GiteaMirror commented

2026-04-22 12:27:48 -05:00

Originally created by @eliranwong on GitHub (Feb 17, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9180

What is the issue?

Hi, I've just done a quick speed test with Ollama and Llama.cpp, using the same model files, on my iGPU-only device.

Below are the results:

Ollama Speed Test Result

LLama.cpp Speed Test Result with CPU backend

LLama.cpp Speed Test Result with ROCm backend

Ollama speed is slight slower than Llama.cpp with CPU backend, but much slower than Llama.cpp with ROCm backend. It appears to me that Ollama may have a chance not running with ROCm backend. Did I miss something?

Relevant log output

[Ollama Speed Test Result](https://github.com/eliranwong/MultiAMDGPU_AIDev_Ubuntu/blob/main/igpu_only/GPD_Pocket_4.md#speed-test-with-ollama)

[LLama.cpp Speed Test Result with CPU backend](https://github.com/eliranwong/MultiAMDGPU_AIDev_Ubuntu/blob/main/igpu_only/GPD_Pocket_4.md#test-speed-with-llamacpp---cpu-backend)

[LLama.cpp Speed Test Result with ROCm backend](https://github.com/eliranwong/MultiAMDGPU_AIDev_Ubuntu/blob/main/igpu_only/GPD_Pocket_4.md#test-speed-with-llamacpp---rocm-backend)

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.5.11

Originally created by @eliranwong on GitHub (Feb 17, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9180 ### What is the issue? Hi, I've just done a quick speed test with Ollama and Llama.cpp, using the same model files, on my iGPU-only device. Below are the results: [Ollama Speed Test Result](https://github.com/eliranwong/MultiAMDGPU_AIDev_Ubuntu/blob/main/igpu_only/GPD_Pocket_4.md#speed-test-with-ollama) [LLama.cpp Speed Test Result with CPU backend](https://github.com/eliranwong/MultiAMDGPU_AIDev_Ubuntu/blob/main/igpu_only/GPD_Pocket_4.md#test-speed-with-llamacpp---cpu-backend) [LLama.cpp Speed Test Result with ROCm backend](https://github.com/eliranwong/MultiAMDGPU_AIDev_Ubuntu/blob/main/igpu_only/GPD_Pocket_4.md#test-speed-with-llamacpp---rocm-backend) Ollama speed is slight slower than Llama.cpp with CPU backend, but much slower than Llama.cpp with ROCm backend. It appears to me that Ollama may have a chance not running with ROCm backend. Did I miss something? ### Relevant log output ```shell [Ollama Speed Test Result](https://github.com/eliranwong/MultiAMDGPU_AIDev_Ubuntu/blob/main/igpu_only/GPD_Pocket_4.md#speed-test-with-ollama) [LLama.cpp Speed Test Result with CPU backend](https://github.com/eliranwong/MultiAMDGPU_AIDev_Ubuntu/blob/main/igpu_only/GPD_Pocket_4.md#test-speed-with-llamacpp---cpu-backend) [LLama.cpp Speed Test Result with ROCm backend](https://github.com/eliranwong/MultiAMDGPU_AIDev_Ubuntu/blob/main/igpu_only/GPD_Pocket_4.md#test-speed-with-llamacpp---rocm-backend) ``` ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.5.11

GiteaMirror added the performance bug amd labels 2026-04-22 12:27:48 -05:00

GiteaMirror commented

2026-04-22 12:27:51 -05:00

@eliranwong commented on GitHub (Feb 18, 2025):

Remarks: On my another device, having dual discrete AMD GPUs, both Ollama and Llama.cpp runs with similar speed. The issue mentioned above is spotted on a iGPU-only device.

@eliranwong commented on GitHub (Feb 18, 2025): Remarks: On my another device, having dual discrete AMD GPUs, both Ollama and Llama.cpp runs with similar speed. The issue mentioned above is spotted on a iGPU-only device.

GiteaMirror commented

2026-04-22 12:27:52 -05:00

@rick-github commented on GitHub (Feb 18, 2025):

Server logs may aid in debugging.

@rick-github commented on GitHub (Feb 18, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may aid in debugging.

GiteaMirror commented

2026-04-22 12:27:54 -05:00

@elarbor commented on GitHub (Feb 18, 2025):

我也想知道部署后怎么对外调用http api

@elarbor commented on GitHub (Feb 18, 2025): 我也想知道部署后怎么对外调用http api

GiteaMirror commented

2026-04-22 12:27:55 -05:00

@eliranwong commented on GitHub (Feb 18, 2025):

Server logs may aid in debugging.

Appreciate your help. Here is the server log.

server_log_output.txt

From the server log, I spot these lines may be relevant:

Feb 16 07:31:24 ai ollama[1781]: time=2025-02-16T07:31:24.513Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
Feb 16 07:31:24 ai ollama[1781]: time=2025-02-16T07:31:24.525Z level=WARN source=amd_linux.go:61 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory"
Feb 16 07:31:24 ai ollama[1781]: time=2025-02-16T07:31:24.533Z level=WARN source=amd_linux.go:376 msg="amdgpu is not supported (supported types:[gfx1030 gfx1100 gfx1101 gfx1102 gfx900 gfx906 gfx908 gfx90a gfx940 gfx941 gfx942])" gpu_type=gfx1150 gpu=0 library=/usr/local/lib/ollama/rocm

Particularly, in my case, I need Ollama to support gfx type gfx1151, as I am running a RDNA-3.5-based iGPU, AMD Radeon™ 890M.

Information below may also help:

I am using ROCm version: 6.3.2

When I run:

ls /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx*.dat

/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1010.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1012.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1030.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1100.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1101.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1102.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1151.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1200.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1201.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx900.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx906.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx908.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx90a.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx942.dat

@eliranwong commented on GitHub (Feb 18, 2025): > [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may aid in debugging. Appreciate your help. Here is the server log. [server_log_output.txt](https://github.com/user-attachments/files/18839087/server_log_output.txt) From the server log, I spot these lines may be relevant: ``` Feb 16 07:31:24 ai ollama[1781]: time=2025-02-16T07:31:24.513Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" Feb 16 07:31:24 ai ollama[1781]: time=2025-02-16T07:31:24.525Z level=WARN source=amd_linux.go:61 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory" Feb 16 07:31:24 ai ollama[1781]: time=2025-02-16T07:31:24.533Z level=WARN source=amd_linux.go:376 msg="amdgpu is not supported (supported types:[gfx1030 gfx1100 gfx1101 gfx1102 gfx900 gfx906 gfx908 gfx90a gfx940 gfx941 gfx942])" gpu_type=gfx1150 gpu=0 library=/usr/local/lib/ollama/rocm ``` Particularly, in my case, I need Ollama to support gfx type `gfx1151`, as I am running a RDNA-3.5-based iGPU, AMD Radeon™ 890M. Information below may also help: I am using ROCm version: 6.3.2 When I run: > ls /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx*.dat ```output /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1010.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1012.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1030.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1100.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1101.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1102.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1151.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1200.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1201.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx900.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx906.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx908.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx90a.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx942.dat ```

GiteaMirror commented

2026-04-22 12:27:57 -05:00

@eliranwong commented on GitHub (Feb 18, 2025):

我也想知道部署后怎么对外调用http api

我不肯定是否完全明白您的提問，Ollama server 本身有 http api，llama.cpp 可用 llama-server, 從開發或用戶而言，我相信有好多方式，我個人用 AgentMake 支援 Ollama 和 Llama.cpp

@eliranwong commented on GitHub (Feb 18, 2025): > 我也想知道部署后怎么对外调用http api 我不肯定是否完全明白您的提問，Ollama server 本身有 http api，llama.cpp 可用 [llama-server](https://github.com/ggml-org/llama.cpp#llama-server), 從開發或用戶而言，我相信有好多方式，我個人用 [AgentMake](https://github.com/eliranwong/agentmake) 支援 Ollama 和 Llama.cpp

GiteaMirror commented

2026-04-22 12:27:57 -05:00

@rick-github commented on GitHub (Feb 18, 2025):

Have you tried overriding driver selection by setting HSA_OVERRIDE_GFX_VERSION?

@rick-github commented on GitHub (Feb 18, 2025): Have you tried overriding driver selection by setting [`HSA_OVERRIDE_GFX_VERSION`](https://github.com/ollama/ollama/blob/main/docs/gpu.md#overrides-on-linux)?

GiteaMirror commented

2026-04-22 12:27:58 -05:00

@eliranwong commented on GitHub (Feb 18, 2025):

Have you tried overriding driver selection by setting HSA_OVERRIDE_GFX_VERSION?

I tried to use with and without HSA_OVERRIDE_GFX_VERSION, no difference in terms of speed with Ollama. But with llama.cpp speed is much faster with HSA_OVERRIDE_GFX_VERSION=11.5.1. No difference for Ollama.

I wrote some notes about the choice of 11.5.1 at https://github.com/eliranwong/MultiAMDGPU_AIDev_Ubuntu/blob/main/igpu_only/GPD_Pocket_4.md#remarks-about-hsa_override_gfx_version

By default, gfx number in rocminfo output is gfx1150, but overriding with HSA_OVERRIDE_GFX_VERSION=11.5.1 works for llama.cpp only.

@eliranwong commented on GitHub (Feb 18, 2025): > Have you tried overriding driver selection by setting [`HSA_OVERRIDE_GFX_VERSION`](https://github.com/ollama/ollama/blob/main/docs/gpu.md#overrides-on-linux)? I tried to use with and without HSA_OVERRIDE_GFX_VERSION, no difference in terms of speed with Ollama. But with llama.cpp speed is much faster with `HSA_OVERRIDE_GFX_VERSION=11.5.1`. No difference for Ollama. I wrote some notes about the choice of `11.5.1` at https://github.com/eliranwong/MultiAMDGPU_AIDev_Ubuntu/blob/main/igpu_only/GPD_Pocket_4.md#remarks-about-hsa_override_gfx_version By default, gfx number in `rocminfo` output is gfx1150, but overriding with `HSA_OVERRIDE_GFX_VERSION=11.5.1` works for llama.cpp only.

GiteaMirror commented

2026-04-22 12:27:59 -05:00

@eliranwong commented on GitHub (Feb 19, 2025):

I put all together the setup notes of ROCm, ollama, and llama.cpp at https://github.com/eliranwong/AMD_iGPU_AI_Setup, for your reference.

@eliranwong commented on GitHub (Feb 19, 2025): I put all together the setup notes of ROCm, ollama, and llama.cpp at https://github.com/eliranwong/AMD_iGPU_AI_Setup, for your reference.

GiteaMirror commented

2026-04-22 12:28:00 -05:00

@eliranwong commented on GitHub (Feb 25, 2025):

An update: I also tested llama.cpp that runs Vulkan backend. It is even faster than ROCm backend.

I documented the results at: https://github.com/eliranwong/AMD_iGPU_AI_Setup#speed-tests

If Ollama doesn't support ROCm well, would you consider to add Vulkan support to Ollama?

@eliranwong commented on GitHub (Feb 25, 2025): An update: I also tested llama.cpp that runs Vulkan backend. It is even faster than ROCm backend. I documented the results at: https://github.com/eliranwong/AMD_iGPU_AI_Setup#speed-tests If Ollama doesn't support ROCm well, would you consider to add Vulkan support to Ollama?

GiteaMirror commented

2026-04-22 12:28:01 -05:00

@rick-github commented on GitHub (Feb 25, 2025):

https://github.com/ollama/ollama/pull/5059

@rick-github commented on GitHub (Feb 25, 2025): https://github.com/ollama/ollama/pull/5059

GiteaMirror commented

2026-04-22 12:28:03 -05:00

@eliranwong commented on GitHub (Feb 25, 2025):

An update: I also tested llama.cpp that runs Vulkan backend. It is even faster than ROCm backend.

I documented the results at: https://github.com/eliranwong/AMD_iGPU_AI_Setup#speed-tests

If Ollama doesn't support ROCm well, would you consider to add Vulkan support to Ollama?

sorry, corrected the links for testing Vulkan backends

@eliranwong commented on GitHub (Feb 25, 2025): > An update: I also tested llama.cpp that runs Vulkan backend. It is even faster than ROCm backend. > > I documented the results at: https://github.com/eliranwong/AMD_iGPU_AI_Setup#speed-tests > > If Ollama doesn't support ROCm well, would you consider to add Vulkan support to Ollama? sorry, corrected the links for testing Vulkan backends

GiteaMirror commented

2026-04-22 12:28:04 -05:00

@eliranwong commented on GitHub (Feb 26, 2025):

I think this is the cause of the issue:

When I run:

ls /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx*.dat

/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1010.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1012.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1030.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1100.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1101.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1102.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1151.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1200.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1201.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx900.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx906.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx908.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx90a.dat
/opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx942.dat

However, when I run:

ls /usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx*.dat

/usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx1030.dat
/usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx1100.dat
/usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx1101.dat
/usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx1102.dat
/usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx900.dat
/usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx906.dat
/usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx908.dat
/usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx90a.dat
/usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx940.dat
/usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx941.dat
/usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx942.dat

I think the current ollama library is too old to support gfx1151.

@eliranwong commented on GitHub (Feb 26, 2025): I think this is the cause of the issue: When I run: > ls /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx*.dat ```output /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1010.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1012.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1030.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1100.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1101.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1102.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1151.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1200.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx1201.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx900.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx906.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx908.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx90a.dat /opt/rocm/lib/rocblas/library/TensileLibrary_lazy_gfx942.dat ``` However, when I run: > ls /usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx*.dat ```output /usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx1030.dat /usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx1100.dat /usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx1101.dat /usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx1102.dat /usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx900.dat /usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx906.dat /usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx908.dat /usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx90a.dat /usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx940.dat /usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx941.dat /usr/local/lib/ollama/rocm/rocblas/library/TensileLibrary_lazy_gfx942.dat ``` I think the current ollama library is too old to support `gfx1151`.

GiteaMirror commented

2026-04-22 12:28:05 -05:00

@rick-github commented on GitHub (Feb 26, 2025):

https://github.com/ollama/ollama/pull/9304

@rick-github commented on GitHub (Feb 26, 2025): https://github.com/ollama/ollama/pull/9304

GiteaMirror commented

2026-04-22 12:28:06 -05:00

@eliranwong commented on GitHub (Feb 26, 2025):

#9304

Brilliant! Much appreciated.

@eliranwong commented on GitHub (Feb 26, 2025): > [#9304](https://github.com/ollama/ollama/pull/9304) Brilliant! Much appreciated.

Sign in to join this conversation.

Branches Tags

main

dhiltgen/ci

parth-launch-plan-gating

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

parth-launch-codex-app

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

parth/hide-claude-desktop-till-release

hoyyeva/opencode-image-modality

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#31739