docker/model-runner

View on GitHub

Docker Model Runner

Stars: 651
Forks: 155
Open beginner issues: 0
Indexed issues: 43

Dominant language: Go
License: Apache-2.0
Last GitHub push: Aug 20, 2026
Latest indexed: Sep 20, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: good first issue
PR merge metrics: No merged PRs in 30d

Beginner friendly Everything

Open All

43 open issues indexed

llama.cpp backend: allow `--reasoning on|off` in runtime flag allowlist Open

Difficulty 1/5 Under an hour Newbie friendliness 90/100

docker/model-runner#1064 · Opened Sep 19, 2026
Docker Model Runner (llama.cpp backend) returns HTTP 500 "does not match the expected peg-native format" when a single chat turn requires 2+ sequential tool/function calls Open

Difficulty 4/5 3-5 days Newbie friendliness 68/100

docker/model-runner#1063 · Opened Sep 18, 2026
OrcaRouter provider support for the Docker Model Runner gateway Open

Difficulty 4/5 3-5 days Newbie friendliness 42/100

docker/model-runner#1059 · Opened Sep 9, 2026
Using CPU inference there is no way to control how much ram of the host is used Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

docker/model-runner#1058 · Opened Sep 8, 2026
Docker Model Runner: `docker model bench` leaves the loaded llama.cpp model returning only `?` tokens (CUDA, GTX 1650) Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

docker/model-runner#1056 · Opened Sep 4, 2026
Docker Model Runner on Windows fails to provision com.docker.nv-gpu-info.exe, breaking llama.cpp CUDA backend after Docker Desktop 4.82.0 Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

docker/model-runner#1054 · Opened Sep 1, 2026
SSRF fix in PR #1038 blocks all private/loopback/link-local realm addresses, breaking internal/corporate registries Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

docker/model-runner#1050 · 1 reaction · Opened Aug 24, 2026
`/api/show` returns no `capabilities` and empty `details` fields Open

Difficulty 3/5 1-2 days Newbie friendliness 64/100

docker/model-runner#1046 · Opened Aug 22, 2026
`ai/functiongemma` tool calls are not parsed into `tool_calls` Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

docker/model-runner#1045 · Opened Aug 22, 2026
diffusers: generation continues after client disconnect and blocks the event loop — no cancellation Open

Difficulty 4/5 3-5 days Newbie friendliness 52/100

docker/model-runner#1041 · Opened Aug 15, 2026
Gemma 4 on llama: Reasoning budget 0 does not work Open

Difficulty 3/5 1-2 days Newbie friendliness 55/100

docker/model-runner#1039 · Opened Aug 11, 2026
compose up: --backend flag is accepted but never applied Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

docker/model-runner#1036 · Opened Aug 10, 2026
Compose: allowlisted backend environment variables for inference process Open

Difficulty 4/5 3-5 days Newbie friendliness 52/100

docker/model-runner#1035 · Opened Aug 10, 2026
Disable thinking if reasoning_effort is none. Open

Difficulty 3/5 1-2 days Newbie friendliness 62/100

docker/model-runner#1028 · Opened Jul 27, 2026
configure --context-size applied nondeterministically; packaged 128K default loaded instead → kernel panic on 24GB Mac (3×) Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

docker/model-runner#1025 · Opened Jul 24, 2026
Pascal GPUs (sm_61/sm_62) still fall back to CPU with `docker model run` despite #986 Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

docker/model-runner#1024 · 2 reactions · Opened Jul 23, 2026
vLLM support broken on Windows with WSL2 Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

docker/model-runner#1018 · 2 comments · 2 reactions · Opened Jul 18, 2026
Release the binary for the Docker CLI plugin `docker-model-plugin` Open

Difficulty 4/5 3-5 days Newbie friendliness 52/100

docker/model-runner#1016 · Opened Jul 15, 2026
Disk Usage Duplication Open

Difficulty 4/5 3-5 days Newbie friendliness 38/100

docker/model-runner#1015 · 2 comments · 1 reaction · Opened Jul 14, 2026
automatic unloading mechanism in Docker Model, similar to the one in Ollama Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

docker/model-runner#1014 · Opened Jul 14, 2026
More apple metal woes Open

Difficulty 4/5 3-5 days Newbie friendliness 38/100

docker/model-runner#1009 · 3 comments · Opened Jul 12, 2026
Available unified memory in llama.cpp Open

good first issue

Difficulty 4/5 3-5 days Newbie friendliness 45/100

docker/model-runner#994 · 1 comment · Opened Jul 3, 2026
Docker pull fails for ai/llama3.2 with TLS handshake timeout (500 Internal Server Error) Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

docker/model-runner#989 · Opened Jun 28, 2026
CUDA version requirement is too new Open

Difficulty 4/5 3-5 days Newbie friendliness 42/100

docker/model-runner#978 · Opened Jun 19, 2026
latest model runner seems to have a few issues Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

docker/model-runner#969 · 3 comments · 2 reactions · Opened Jun 12, 2026
docker model package doesn't inherent model features ( no vision decoding ) Open

Difficulty 3/5 1-2 days Newbie friendliness 50/100

docker/model-runner#963 · 1 reaction · Opened Jun 9, 2026
docker model package don't update context size Open

Difficulty 3/5 1-2 days Newbie friendliness 48/100

docker/model-runner#962 · 3 comments · Opened Jun 9, 2026
Suggestion about model reinstall-runner Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

docker/model-runner#958 · Opened Jun 6, 2026
VLLM CUDA image doesn't run on GPU Open

Difficulty 3/5 1-2 days Newbie friendliness 55/100

docker/model-runner#952 · 4 comments · 7 reactions · Opened Jun 2, 2026
Model MTP support + Backend Issue Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

docker/model-runner#941 · 3 comments · Opened May 26, 2026
Bug Report: Docker Model Runner Does Not Use Intel Arc GPU via Vulkan on Windows Open

good first issue

Difficulty 4/5 3-5 days Newbie friendliness 50/100

docker/model-runner#925 · 2 comments · 1 reaction · Opened May 20, 2026
Docker Sandboxes and DMR integration Open

good first issue

docker/model-runner#915 · 3 comments · 1 assignee · Opened May 14, 2026
Unable to set vllm serve parameters using hf_overrides Open

good first issue

Difficulty 4/5 3-5 days Newbie friendliness 50/100

docker/model-runner#912 · 13 comments · Opened May 12, 2026
NPU support Open

good first issue

Difficulty 5/5 Over a week Newbie friendliness 35/100

docker/model-runner#864 · 5 comments · Opened Apr 14, 2026
flash streaming Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

docker/model-runner#815 · Opened Mar 30, 2026
Several issues displaying log files Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

docker/model-runner#750 · 7 comments · Opened Mar 14, 2026
docker model launch llmfit Open

good first issue

Difficulty 4/5 3-5 days Newbie friendliness 42/100

docker/model-runner#747 · 9 comments · Opened Mar 14, 2026
Runtime_flags are ignored on Linux in certain cases Open

Difficulty 4/5 3-5 days Newbie friendliness 38/100

docker/model-runner#726 · 8 comments · Opened Mar 3, 2026
Add support for Modelfile Open

good first issue

Difficulty 4/5 3-5 days Newbie friendliness 48/100

docker/model-runner#613 · 2 comments · Opened Jan 29, 2026
Host-side TCP setting blocks vLLM backend installation Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 48/100

docker/model-runner#526 · 7 comments · 3 reactions · Opened Dec 18, 2025
`unable to load runner: error waiting for runner to be ready: llama.cpp terminated unexpectedly` Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 48/100

docker/model-runner#479 · 17 comments · 1 reaction · Opened Dec 4, 2025
alt (option) + b/f doesn't work on iTerm2 on macOS Open

good first issue

docker/model-runner#234 · 2 comments · 1 reaction · 2 assignees · Opened Oct 15, 2025
Feature: MLX backend Open

enhancement good first issue

docker/model-runner#90 · 6 comments · 5 reactions · 1 assignee · Opened Jun 21, 2025

docker/model-runner

Get new issues in your inbox