khluuandCodex e8a795da4a Fix CUDA 12 DeepEP NCCL pin ...

Co-authored-by: Codex <noreply@openai.com>

Signed-off-by: khluu <khluu000@gmail.com>

2026-07-29 03:39:24 -07:00

..

entrypoints

[Docker] Non-root support for vllm-openai; add opt-in vllm-openai-nonroot target (#40275)

2026-05-25 13:45:31 +08:00

ci-rocm.hcl

[ROCm] Upgrade NIXL and UCX (#49251)

2026-07-21 22:30:02 -05:00

docker-bake-rocm.hcl

[ROCm] Upgrade NIXL and UCX (#49251)

2026-07-21 22:30:02 -05:00

docker-bake.hcl

build: embed image provenance metadata in vLLM containers (#40653)

2026-04-29 03:07:41 -07:00

Dockerfile

Fix CUDA 12 DeepEP NCCL pin

2026-07-29 03:39:24 -07:00

Dockerfile.cpu

[CI/Build][CPU] Remove global extra index (#47687)

2026-07-06 13:42:01 +08:00

Dockerfile.ppc64le

Improvement of Docker image build for IBM Power using prebuilt wheels from IBM published devpi index (#46017)

2026-07-08 13:01:14 +00:00

Dockerfile.rocm

[ROCm][CI] Prepare AMD mirrors for regating (#49270)

2026-07-23 18:42:25 -07:00

Dockerfile.rocm_base

[ROCm][Docker] Drop MORI_GPU_ARCHS so MoRI autodetects the device arch (#49737)

2026-07-24 21:14:03 +00:00

Dockerfile.s390x

[CPU] Fix s390x builds and update torch version in dockerfile (#50144)

2026-07-29 12:52:17 +08:00

Dockerfile.tpu

Always use cache mounts when installing vllm to avoid populating pip cache in the image. Also remove apt cache. (#23270)

2025-08-21 18:01:03 -04:00

Dockerfile.xpu

[XPU] upgrade to torch 2.13 (#48677)

2026-07-29 01:24:56 -07:00

versions.json

[WideEP] Update NCCL to 2.30.7 to enable DeepEPv2 in the vllm/vllm-openai image (#45321)

2026-07-24 13:00:02 -07:00