0 Fork 0

Files

T

hsliu_ustc 77dab60bf7 [Doc] Keep ROCm run examples on the published v0.28.0 image tag

The release pipeline builds and publishes only the CUDA image
(.buildkite/release/release-pipeline.yml builds docker/Dockerfile.cuda;
publish-release-images.sh targets vllm/vllm-omni). The prebuilt ROCm
image is uploaded out-of-band, and v0.28.0 is the latest tag confirmed
live on Docker Hub (#7405). Revert the two docker run examples to
v0.28.0 and state why the tag lags the 0.30.0 wheels, so users do not
hit a missing-tag pull failure. Source-build examples stay on the
upstream vllm/vllm-openai-rocm:v0.30.0 base, which is published.

Signed-off-by: hsliu_ustc <hsliu_ustc@noreply.gitcode.com>

2026-09-27 07:05:58 +08:00

gpu

[Doc] Keep ROCm run examples on the published v0.28.0 image tag

2026-09-27 07:05:58 +08:00

npu

[Doc] Update README and docs for v0.30.0

2026-09-26 17:53:59 +08:00

.nav.yml

[Docs] optimize and supplement docs system (#86 )

2025-11-28 11:03:52 +08:00

gpu.md

[Doc] Update README and docs for v0.30.0

2026-09-26 17:53:59 +08:00

npu.md

[NPU] Upgrade to v0.16.0 (#1375 )

2026-02-26 14:26:50 +08:00

python_env_setup.inc.md

[Docs] optimize and supplement docs system (#86 )

2025-11-28 11:03:52 +08:00

README.md

[Doc] Update README and docs for v0.30.0

2026-09-26 17:53:59 +08:00

README.md

Installation

!!! important vLLM-Omni is released against the matching upstream vLLM major/minor version. The vLLM-Omni 0.30.x release line uses vLLM 0.30.x; the source-install instructions pin vLLM 0.30.0.

vLLM-Omni supports the following hardware platforms: