Skip to content

Pull requests: flashinfer-ai/flashinfer

New pull request New
49 Open 1,051 Closed
49 Open 1,051 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

perf: add 1x4x1 cluster shape for fp8 bmm M<16 cases
#1473 opened Aug 12, 2025 by ttyio Loading…
5 tasks
2
feat: Enable multiple fused-moe backends
#1472 opened Aug 12, 2025 by amirkl94 Loading…
3
Remove __restrict__ extension to fix compilation error on GB200
#1470 opened Aug 12, 2025 by 842974287 Loading…
5 tasks
6
fix: remove redundant zero_init reverted by #1459
#1463 opened Aug 11, 2025 by yyihuang • Draft
5 tasks
9
Fix TRTLLM NVFP4-out attention kernel scale factor dim issue
#1460 opened Aug 11, 2025 by elvischenv Loading…
4 of 5 tasks
11
feat(attention): add RoPE offset support for batch prefill
#1457 opened Aug 11, 2025 by MengAiDev Loading…
3 tasks done
4
Fix cuda-python v13.0 import compatibility
#1455 opened Aug 11, 2025 by yongwww Loading…
3 of 5 tasks
7
feat: enable trtllm-gen attn speculative decoding verify by decode
#1453 opened Aug 11, 2025 by yyihuang • Draft
5 tasks
@yzh119 @yyihuang
4
benchmark: add allreduce_fusion benchmark
#1450 opened Aug 10, 2025 by yyihuang • Draft
5 tasks
@yyihuang
6
Remove getEnvEnablePDL in favor of enable_pdl parameter
#1446 opened Aug 10, 2025 by yongwww • Draft
5 tasks
@cyx-6
15
refactor: unify autotuner for fp4 gemm backends
#1439 opened Aug 8, 2025 by ttyio Loading…
3 of 5 tasks
4
misc: Fix persistent kernel compilation
#1430 opened Aug 8, 2025 by Edenzzzz Loading…
5 tasks
3
Sink attention AoT
#1427 opened Aug 8, 2025 by nandor Loading…
5 tasks done
7
Restore llama4 fc2 required kernels
#1417 opened Aug 8, 2025 by aleozlx Loading…
5 tasks done
6
refactor: update trtllm-gen attn interface
#1407 opened Aug 7, 2025 by yyihuang • Draft
5 tasks
@yyihuang
4
gpt-oss: Add MXFP8 x MXFP4 CUTLASS MOE for SM100 and BF16 x MXFP4 CUTLASS for SM90 + SwigluBias Activation
#1396 opened Aug 6, 2025 by djmmoss Loading…
4 of 5 tasks
3
misc: Customize kv lens buffer size for sparse attention
#1383 opened Aug 5, 2025 by Edenzzzz Loading…
5 tasks
1
6
Removes MPI dependency from MNNVL AllReduce
#1379 opened Aug 4, 2025 by pranavm-nvidia Loading…
5 tasks
6
Unify and modularize decode and prefill test.
#1375 opened Aug 4, 2025 by weireweire Loading…
5 tasks done
18
feat: Support sliding window for persistent kernel
#1368 opened Aug 3, 2025 by Edenzzzz Loading…
5 tasks
7
feat: support dynamic scale factor interface for trtllm-gen attn
#1342 opened Jul 29, 2025 by yyihuang • Draft
3 of 5 tasks
@yzh119
3
[WIP]: Masked layout fp4 gemm using cute-dsl
#1331 opened Jul 25, 2025 by yzh119 • Draft
5 tasks
@yyihuang
1
refactor: Improved metainfo for trtllm-gen kernels
#1328 opened Jul 25, 2025 by cyx-6 Loading…
5 tasks
13
Add moe benchmark routine
#1327 opened Jul 25, 2025 by aleozlx • Draft
3 of 5 tasks
6
Add k_scale and v_scale to persistent attention
#1322 opened Jul 24, 2025 by Edenzzzz Loading…
5 tasks
9
ProTip! Add no:assignee to see everything that’s not assigned.