forked from vllm-project/vllm
-
Notifications
You must be signed in to change notification settings - Fork 6
Pull requests: EmbeddedLLM/vllm
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[ROCm] Enable VLLM triton FP8 moe for gfx1201, tuned for Qwen3-30B-A3B-FP8 tp=2
#79
opened Mar 12, 2026 by
big-yellow-duck
Loading…
2 of 5 tasks
[ROCm] Enable aiter group quant FP8 for RDNA4 gpus
#78
opened Mar 12, 2026 by
big-yellow-duck
Loading…
3 of 5 tasks
[ROCm] Enable Aiter ck_gemm_a8w8_blockscale for RDNA4 gpus. Qwen3.5-27B-FP8 tp=2, Qwen3-0.6B-FP8 tp=1
#77
opened Mar 12, 2026 by
big-yellow-duck
Loading…
2 of 5 tasks
ProTip!
Exclude everything labeled
bug with -label:bug.