Files
grace-gpu-containers/vllm/Dockerfile
biondizzle 10c71a446c Remove flash-attn GIT_TAG override to main — causes FLASHATTENTION_FP8_TWO_LEVEL_INTERVAL undefined error
v0.19.0 pins a compatible flash-attn commit (2921022). The sed that
forced GIT_TAG to main pulled in newer code that references
FLASHATTENTION_FP8_TWO_LEVEL_INTERVAL which isn't defined in v0.19.0's
build config. Use the pinned commit instead.
2026-04-28 03:07:14 +00:00

11 KiB