forked from vllm-project/vllm
-
Notifications
You must be signed in to change notification settings - Fork 28
Pull requests: ROCm/vllm
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[FEAT] Improved PagedAttention FP8 (faster kvcache dequant v1)
#346
opened Dec 24, 2024 by
tjtanaa
Loading…
[Kernel] Upload a MoE config file for Mixtral8x7B 8GPU on AMD_Instinct_MI300X_OAM machine (fp16)
#261
opened Nov 4, 2024 by
Jacob0226
Loading…
ProTip!
Exclude everything labeled
bug
with -label:bug.