daviestechlabs/kuberay-images
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(strixhalo): add all missing vllm runtime deps for v1.0.23
Some checks failed
Build and Push Images / build (Dockerfile.ray-worker-intel, intel) (push) Has been cancelled
Details
Build and Push Images / build (Dockerfile.ray-worker-nvidia, nvidia) (push) Has been cancelled
Details
Build and Push Images / build (Dockerfile.ray-worker-rdna2, rdna2) (push) Has been cancelled
Details
Build and Push Images / build (Dockerfile.ray-worker-strixhalo, strixhalo) (push) Has been cancelled
Details
Build and Push Images / Release (push) Has been cancelled
Details
Build and Push Images / Notify (push) Has been cancelled
Details
Build and Push Images / determine-version (push) Has been cancelled
Details

Browse Source 
Added: cachetools, ijson, opencv-python-headless, grpcio-reflection,
grpcio-tools, anthropic, mcp, tensorizer (plus pybase64, setproctitle
from prior edit)
This commit is contained in:
Billy Davies
2026-02-09 21:08:52 -05:00
parent 23f239ef69
commit 928a9f89fe
1 changed files with 12 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
dockerfiles/Dockerfile.ray-worker-strixhalo
View File

@@ -204,7 +204,18 @@ RUN --mount=type=cache,target=/root/.cache/uv \
'einops>=0.7.0' \ 'einops>=0.7.0' \
'depyf>=0.18.0' \ 'depyf>=0.18.0' \
'grpcio>=1.60.0' \ 'grpcio>=1.60.0' \
'protobuf>=4.25.0' 'protobuf>=4.25.0' \
'pybase64>=1.0' \
'setproctitle>=1.3.0' \
# ── additional vllm deps missing from --no-deps install ──
'cachetools>=5.0' \
'ijson>=3.2' \
'opencv-python-headless>=4.8' \
'grpcio-reflection>=1.60.0' \
'grpcio-tools>=1.60.0' \
'anthropic>=0.20.0' \
'mcp>=1.0' \
'tensorizer>=2.9.0'
# ── Ray Serve application package ────────────────────────────────────── # ── Ray Serve application package ──────────────────────────────────────
# Baked into the image so the LLM serve app can use the source-built vllm # Baked into the image so the LLM serve app can use the source-built vllm