Roger WangandOpenAI Codex e329dbcb0f [Build] Update DeepEP pin for low-latency fabric support ...

Bump the repo's DeepEP pin to the revision that adds the use_fabric low-latency buffer option required for cross-node MNNVL initialization.

This keeps the runtime DeepEP low-latency fix deployable instead of relying on a local DeepEP build newer than the repo default.

Co-authored-by: OpenAI Codex <codex@openai.com>
Signed-off-by: Roger Wang <hey@rogerw.io>

2026-04-18 18:06:19 -07:00

..

docker-bake.hcl

Add Ubuntu 24.04 support for Docker builds (#35386)

2026-03-24 13:34:44 -07:00

Dockerfile

[Build] Update DeepEP pin for low-latency fabric support

2026-04-18 18:06:19 -07:00

Dockerfile.cpu

[CPU] Refactor CPU affinity and memory management (#39781)

2026-04-17 21:01:08 +08:00

Dockerfile.nightly_torch

Update to transformers v5 (#30566)

2026-04-15 16:29:15 -07:00

Dockerfile.ppc64le

Add structure to requirements/ directory (#39024)

2026-04-10 13:46:41 -07:00

Dockerfile.rocm

[AMD][CI] Update DeepEP branch (#38396)

2026-04-17 14:30:20 -05:00

Dockerfile.rocm_base

[ROCm] [AITER] Revert AITER version to v0.1.10.post3 (#39509)

2026-04-10 16:25:52 +00:00

Dockerfile.s390x

[CPU][IBM Z][Dockefile][Docs] Fix s390x builds for torch 2.11 and update docs for s390x (#39910)

2026-04-15 22:26:21 -07:00

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

Add structure to requirements/ directory (#39024)

2026-04-10 13:46:41 -07:00

versions.json

[Build] Update DeepEP pin for low-latency fabric support

2026-04-18 18:06:19 -07:00