unsloth/docker
Daniel Han 11430aaab5 docker: unbreak standalone vllm serve (ninja-build + flashinfer-jit-cache)
The notebook validation matrix caught the synthetic-data notebook dying
because the vllm server SyntheticDataKit launches never came up. Two
layers to the failure:

1. flashinfer's cpp_ext JIT shells out to ninja. The pip ninja lives in
   the venv bin, which subprocesses like vllm serve do not always
   inherit on PATH, so the JIT failed with exit 127. Install ninja-build
   so the binary is reachable from any PATH.
2. With ninja present the JIT still cannot succeed for device code: the
   runtime image deliberately ships no nvcc. Bake flashinfer-jit-cache
   (cu128) so ops missing from the cubin package (fmha_gen on sm_100a
   was the repro) come precompiled. In-process GRPO never hit this
   because unsloth-zoo blocks the FlashInfer JIT path; standalone
   vllm serve gets no zoo patches.

Fail-soft on the jit-cache for arches without a wheel; the vLLM chain
itself stays fail-loud on amd64.
2026-06-12 11:04:13 +00:00
..
.dockerignore docker: whitelist new build-context files, add docker_confirm.ps1 2026-06-12 05:06:51 +00:00
build.sh Add Docker build for Blackwell that runs on any NVIDIA GPU host 2026-05-24 06:52:58 +00:00
docker_confirm.ps1 docker: install vLLM on the arm64 leg too and probe it in the confirm scripts 2026-06-12 09:09:26 +00:00
docker_confirm.sh docker: install vLLM on the arm64 leg too and probe it in the confirm scripts 2026-06-12 09:09:26 +00:00
Dockerfile docker: unbreak standalone vllm serve (ninja-build + flashinfer-jit-cache) 2026-06-12 11:04:13 +00:00
Dockerfile.studio docker: second review pass fixes 2026-06-12 05:59:52 +00:00
entrypoint.sh docker: review fixes from the 8-reviewer pass and staging CI 2026-06-12 05:31:24 +00:00
fetch_llama_prebuilt.py docker: mirror the llama.cpp bake into build/bin so Studio setup reuses it 2026-06-12 05:12:16 +00:00
freeze.sh Add Docker build for Blackwell that runs on any NVIDIA GPU host 2026-05-24 06:52:58 +00:00
hf_pull.sh hf_{push,pull}.sh: use new hf CLI, fall back to deprecated huggingface-cli 2026-05-24 09:40:22 +00:00
hf_push.sh hf_{push,pull}.sh: use new hf CLI, fall back to deprecated huggingface-cli 2026-05-24 09:40:22 +00:00
run.sh docker: review fixes from the 8-reviewer pass and staging CI 2026-06-12 05:31:24 +00:00
setup_qemu.sh Add linux/arm64 (DGX Spark / Grace) support via QEMU at build time 2026-05-24 10:34:59 +00:00
smoke_test.py [pre-commit.ci] auto fixes from pre-commit.com hooks 2026-06-12 04:35:41 +00:00
studio_launch.sh docker: second review pass fixes 2026-06-12 05:59:52 +00:00
supervisord.conf docker: review fixes from the 8-reviewer pass and staging CI 2026-06-12 05:31:24 +00:00
test_locally.sh docker: review fixes from the 8-reviewer pass and staging CI 2026-06-12 05:31:24 +00:00