Skip to content

Pull requests: flashinfer-ai/flashinfer

New pull request New
25 Open 883 Closed
25 Open 883 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add trtllm-gen attention kernel with FP8 Q/K/V and FP4/FP8 output
#1242 opened Jul 11, 2025 by weireweire Loading…
14
feat: Support MXFP8 x MXFP4 CUTLASS grouped GEMM
#1241 opened Jul 11, 2025 by jinyangyuan-nvidia Loading…
5 tasks
14
add trtllm-gen context attention
#1239 opened Jul 10, 2025 by IwakuraRein Loading…
2 of 5 tasks
10
feat: expose python APIs for cutlass blackwell fmha fp8 kernels
#1238 opened Jul 10, 2025 by yzh119 • Draft
5 tasks
7
feat: Restore convenience FLASHINFER_ENABLE_AOT option
#1235 opened Jul 8, 2025 by mgorny Loading…
3 of 5 tasks
7
[Feature] Support batch prefill for POD Attention
#1231 opened Jul 8, 2025 by Edenzzzz Loading…
6 tasks
1
9
feat: add trtllm-gen mla cubin
#1222 opened Jul 7, 2025 by yyihuang Loading…
5 tasks done
14
Feature/sm100 low latency nvfp4 kernels priority: high
#1214 opened Jul 4, 2025 by azhurkevich Loading…
1 of 5 tasks
@yzh119 @zhyncs
7
Add DeepGEMM kernels
#1209 opened Jul 2, 2025 by cyx-6 Loading…
5 tasks
16
Add ruff to pre-commit
#1201 opened Jul 1, 2025 by cyx-6 • Draft
5 tasks
4
jit: supporting transform output in attention jit template
#1184 opened Jun 27, 2025 by yzh119 • Draft
5 tasks
4
Add mypy to pre-commit
#1179 opened Jun 26, 2025 by cyx-6 • Draft
5 tasks
5
Use flashinfer softmax in top_k_top_p_sampling_from_logits
#1171 opened Jun 24, 2025 by lgeiger Loading…
5 tasks done
11
[wip] Multimem allreduce cutlass dsl
#1169 opened Jun 23, 2025 by Amir-19 • Draft
5 tasks
11
Port AllGather/ReduceScatter from TensorRT-LLM
#1145 opened Jun 15, 2025 by wenscarl Loading…
5 tasks
22
[wip] refactor: add more features to vec_t
#1142 opened Jun 12, 2025 by yzh119 • Draft
5 tasks
28
[WIP] refactor: unifying return status of different backend implementation
#1141 opened Jun 12, 2025 by yzh119 Loading…
5 tasks
2
[wip] ci: update pre-commits
#1094 opened May 26, 2025 by yzh119 Loading…
5 tasks
feat: add mla custom mask
#1017 opened Apr 13, 2025 by yyihuang • Draft
FlashInfer Windows support
#964 opened Mar 21, 2025 by SystemPanic Loading…
[RFC] Redesigned CMake build infrastructure for C++ API
#944 opened Mar 14, 2025 by diptorupd Loading…
6
initial support blackwell
#747 opened Jan 21, 2025 by johnnynunez Loading…
10
[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! Type g p on any issue or pull request to go back to the pull request listing page.