Skip to content

Pull requests: flashinfer-ai/flashinfer

New pull request New
56 Open 1,264 Closed
56 Open 1,264 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

cleanup: ensure repository URL has no trailing slash
#1759 opened Sep 23, 2025 by tarukumar Loading…
3 of 5 tasks
3
[draft]Fix sink attention accuracy regression, add more sink attention test.
#1758 opened Sep 23, 2025 by weireweire Loading…
5 tasks
5
fix: should pass global_override_indptr_cpu in fast_decode_plan param list
#1757 opened Sep 23, 2025 by yyihuang Loading…
5 tasks
feat: Add compute capability checks to flashinfer_benchmark
#1756 opened Sep 23, 2025 by bkryu Loading…
5 tasks done
Fix tests/test_trtllm_gen_attention.py::test_trtllm_batch_prefill, ::test_trtllm_batch_decode mismatch error
#1755 opened Sep 22, 2025 by kahyunnam Loading…
6
bugfix: fix the source path in aot.py
#1740 opened Sep 19, 2025 by yzh119 Loading…
5 tasks done
3
Add comprehensive test xfails tracking system and analysis report
#1733 opened Sep 19, 2025 by Copilot AI • Draft
@yzh119 @Copilot
2
ci/cd: bringup flashinfer-aot-modules package
#1726 opened Sep 19, 2025 by yzh119 Loading…
5 tasks
7
bugfix: partially fix tests/test_trtllm_gen_fused_moe.py unite test failure
#1724 opened Sep 19, 2025 by nv-yunzheq Loading…
5 tasks
5
fix the dequantize_block in the trtllm_cutlass fuse moe test
#1721 opened Sep 18, 2025 by rainj-me Loading…
5 tasks done
9
Tiny optimizations for moe
#1717 opened Sep 18, 2025 by fzyzcjy Loading…
5 tasks
10
misc: Add cuda graph tests for invariant FA2
#1704 opened Sep 17, 2025 by Edenzzzz Loading…
5 tasks
6
misc: fix vector size calculation for fp4
#1702 opened Sep 17, 2025 by yzh119 Loading…
5 tasks
4
refactor: refactor xqa interface
#1701 opened Sep 17, 2025 by yzh119 Loading…
5 tasks
5
[wip] refactor: remove csrc/nv_internal
#1655 opened Sep 9, 2025 by yzh119 Loading…
5 tasks
2
fix: add _check_tensor_params to check correct sampling parameters and dtype validation in decode.py
#1652 opened Sep 8, 2025 by raayandhar Loading…
5 tasks done
13
[WIP] refactor: using tvm-ffi for multi-platform bindings
#1641 opened Sep 5, 2025 by yzh119 Loading…
5 tasks
16
feat: trtllm-gen attention with dynamic scale
#1630 opened Sep 3, 2025 by yyihuang • Draft
5 tasks
re-enable torch.compile
#1576 opened Aug 26, 2025 by guilhermeleobas Loading…
4 of 5 tasks
2
Support input and output signals for cutedsl gemm
#1569 opened Aug 25, 2025 by fzyzcjy • Draft
5 tasks
1
feat: add lse return on trtllm-gen attention priority: high
#1566 opened Aug 24, 2025 by yyihuang • Draft
5 tasks
@yzh119
6
feat: support radix-based top-k sampling algorithm
#1561 opened Aug 24, 2025 by JasonJ2021 Loading…
4 of 5 tasks
27
[CuTe DSL] Add Blackwell MHA prefill and MLA decode kernel
#1549 opened Aug 22, 2025 by dubcyfor3 • Draft
4 of 5 tasks
2
Auto tuning cutedsl gemm
#1527 opened Aug 21, 2025 by fzyzcjy Loading…
5 tasks
@yyihuang
3
tests(attn): add short-seq CUDA edge-case test (qo_len=1) for prefill
#1515 opened Aug 19, 2025 by PrithviElancherran Loading…
3 tasks done
5
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.