forked from flashinfer-ai/flashinfer
-
Notifications
You must be signed in to change notification settings - Fork 8
Pull requests: AMD-Ecosystem/flashinfer
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Point the Gemma benchmark routines at a capability that exists
#369
opened Sep 13, 2026 by
demandal25
Collaborator
Loading…
6 tasks done
fp8 KV cache in the in-tree prefill kernel, and the refusals around it
#368
opened Sep 12, 2026 by
demandal25
Collaborator
Loading…
10 tasks done
Route short-query paged prefill to fa2, at 1.19-6.08x over AITER
#367
opened Sep 12, 2026 by
demandal25
Collaborator
Loading…
10 tasks done
fp8 paged prefill on the AITER route, at 1.22-1.66x over bf16
#366
opened Sep 12, 2026 by
demandal25
Collaborator
Loading…
7 tasks done
Reach AITER's asm prefill arm, and route to it on CDNA4
#365
opened Sep 12, 2026 by
demandal25
Collaborator
Loading…
8 of 10 tasks
Support speculative-decode verify on ROCm, and stop auto routing short-query prefill to AITER
#362
opened Sep 12, 2026 by
demandal25
Collaborator
Loading…
12 tasks done
ProTip!
Mix and match filters to narrow down what you’re looking for.