Skip to content

Pull requests: flashinfer-ai/flashinfer

New pull request New
Clear current search query, filters, and sorts
13 Open 713 Closed
13 Open 713 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

perf: use cub's native BlockLoad/BlockStore for sampling kernels
#309 opened Jun 17, 2024 by yzh119 • Draft
perf: Fail fast on empty query for BatchPrefillWithPagedKVCacheKernel
#377 opened Jul 17, 2024 by Yard1 • Draft
2
[WIP][AMDGPU] try rocm POC
#491 opened Sep 4, 2024 by yiakwy-xpu-ml-framework-team • Draft
16
Allow AOT builds to be generated without aux kernels
#723 opened Jan 8, 2025 by nandor
feat: implement SM-Constrained GEMM API
#744 opened Jan 21, 2025 by lanchongyizu
3
initial support blackwell
#747 opened Jan 21, 2025 by johnnynunez
9
[RFC] Redesigned CMake build infrastructure for C++ API
#944 opened Mar 14, 2025 by diptorupd
1
Implement SM_constraint GEMM with triton
#950 opened Mar 17, 2025 by yyihuang
1
perf: Use 2WG pipeline design for MLA implementation on Hopper
#952 opened Mar 17, 2025 by yzh119
Fix compilation with FP16_QK_REDUCTION enabled.
#962 opened Mar 19, 2025 by diptorupd
2
FlashInfer Windows support
#964 opened Mar 21, 2025 by SystemPanic
[Refactor] Uniform PoDAttention API with Horizontal Fusion SMs Schedule
#967 opened Mar 21, 2025 by happierpig
1
Allow passing workspace base directory via environment variable
#973 opened Mar 26, 2025 by jsuchome
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.