Skip to content

Pull requests: flashinfer-ai/flashinfer

New pull request New
10 Open 597 Closed
10 Open 597 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

fix: Pass backend in BatchPrefillWith*KVCacheWrapper.plan()
#808 opened Feb 12, 2025 by sfc-gh-yewang Loading…
1
feat: support MLA decode, implemented by CuTe targeted to SM80
#766 opened Jan 31, 2025 by tsu-bin Loading…
5
refactor: change to TORCH_LIBRARY
#764 opened Jan 29, 2025 by youkaichao Loading…
21
initial support blackwell
#747 opened Jan 21, 2025 by johnnynunez Loading…
8
feat: implement SM-Constrained GEMM API
#744 opened Jan 21, 2025 by lanchongyizu Loading…
3
Allow AOT builds to be generated without aux kernels
#723 opened Jan 8, 2025 by nandor Loading…
Improve error message when TORCH_CUDA_ARCH_LIST has many supported architechtures.
#686 opened Dec 19, 2024 by pavanimajety Loading…
1
[WIP][AMDGPU] try rocm POC
#491 opened Sep 4, 2024 by yiakwy-xpu-ml-framework-team • Draft
16
perf: Fail fast on empty query for BatchPrefillWithPagedKVCacheKernel
#377 opened Jul 17, 2024 by Yard1 • Draft
2
perf: use cub's native BlockLoad/BlockStore for sampling kernels
#309 opened Jun 17, 2024 by yzh119 • Draft
ProTip! Add no:assignee to see everything that’s not assigned.