vllm/docker at ff00ef309dc619752c4c22028583e36a6f7e37a1 - vllm

mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-03 04:27:03 +08:00

History

westers ff00ef309d Fix Dockerfile.rocm to set VLLM_TARGET_DEVICE=rocm

Without this environment variable, the build defaults to VLLM_TARGET_DEVICE=cuda
as defined in vllm/envs.py, causing cmake to configure with -DVLLM_TARGET_DEVICE=cuda
instead of -DVLLM_TARGET_DEVICE=rocm.

This fix ensures ROCm Docker builds use the correct target device.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

Signed-off-by: westers <steve.westerhouse@origami-analytics.com>

2025-12-20 10:21:34 -06:00

Dockerfile

[docker] Allow kv_connectors install to fail on arm64 (#30806 )

2025-12-16 16:41:57 -08:00

Dockerfile.cpu

[CPU] Refactor CPU fused MOE (#30531 )

2025-12-18 14:36:49 +08:00

Dockerfile.nightly_torch

[Core] Deprecate xformers (#29262 )

2025-11-24 04:18:55 +00:00

Dockerfile.ppc64le

Update Dockerfile to use gcc-toolset-14 and fix test case failures on power (ppc64le) (#28957 )