Skip to content

Pull requests: flashinfer-ai/flashinfer

New pull request New
116 Open 1,801 Closed
116 Open 1,801 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

benchmark: Enable speculative decode microbenchmarking for paged decode
#2628 opened Feb 24, 2026 by bkryu Loading…
5 tasks done
5
fix: trtllm_mxint4_block_scale_moe unit test to index output list
#2627 opened Feb 24, 2026 by jimmyzho Loading…
5 tasks
2
Protect against null clusterUuid in mnnvl.py
#2626 opened Feb 23, 2026 by akshaver Loading…
4 of 5 tasks
4
feat: Fuse shared experts into trtllm_gen moe (fp8) run-ci
#2625 opened Feb 23, 2026 by nv-yunzheq Loading…
5 tasks
12
allow cudnn to be chosen for prefill
#2622 opened Feb 23, 2026 by scottyokim Loading…
5 tasks
10
feat: add pool+indices support to gated_delta_rule_decode_pretranspose (bf16 path)
#2619 opened Feb 22, 2026 by kaixih Loading…
12
perf(gdn): optimize MTP kernel with ILP rows and SMEM v caching
#2618 opened Feb 22, 2026 by ameynaik-hub Loading…
5 tasks done
21
fix: Add tests for the AutoTuner and fix bug in _find_nearest_profile run-ci v0.6.5 release blocker label for v0.6.5
#2617 opened Feb 22, 2026 by danisereb Loading…
4 of 5 tasks
30
feat: port act_and_mul activation kernels to CuTe-DSL
#2616 opened Feb 22, 2026 by bledden Loading…
3 tasks
34
docs: Fix incorrect column-major scale layout in FP8 GEMM docstrings
#2614 opened Feb 21, 2026 by bledden Loading…
1
2
fix: Support non-power-of-2 dimensions in act_and_mul kernels run-ci
#2613 opened Feb 21, 2026 by bledden Loading…
1
27
fix: use type-specific FP8 max value for clamping in RMSNorm quantization kernels run-ci
#2612 opened Feb 21, 2026 by Bias92 Loading…
8
support qk_nope_head_dim for 192 check for GLM-5 run-ci
#2607 opened Feb 21, 2026 by rainj-me Loading…
5 tasks done
10
[bugfix] Fix FilteredTopK overflow correctness run-ci
#2605 opened Feb 20, 2026 by jiangyinzuo Loading…
6 tasks done
1
40
feat: support FP8 concat_mla_k for FP8 MLA prefill
#2603 opened Feb 20, 2026 by hypdeb Loading…
9
[DRAFT][DO NOT MERGE] Test tvm-ffi 0.1.9rc
#2599 opened Feb 20, 2026 by yongwww • Draft
5 tasks
26
feat: add CuTe DSL flash attention backend for SM120 GPUs
#2598 opened Feb 20, 2026 by blake-snc Loading…
10
Bf16 routed moe
#2594 opened Feb 19, 2026 by IwakuraRein Loading…
5 tasks
13
feat: Add comprehensive performance optimization ecosystem
#2593 opened Feb 19, 2026 by divyanshu-iitian Loading…
5 tasks
25
[BugFix] guard against uint32 underflow in multi-CTA TopK chunk calculation
#2592 opened Feb 19, 2026 by LopezCastroRoberto Loading…
12
Perf: Optimize GDN decode pretranspose kernel for all batch sizes
#2588 opened Feb 19, 2026 by ameynaik-hub Loading…
5 tasks
9
feat: trtllm tinygemm2 in flashinfer as bf16 routergemm
#2587 opened Feb 19, 2026 by jimmyzho Loading…
5 tasks
14
Additional kernels
#2582 opened Feb 18, 2026 by hypdeb • Draft
8
Implement cutlass_fused_moe mxfp8 run-ci
#2581 opened Feb 18, 2026 by zianglih • Draft
4 of 5 tasks
13
FlashInfer Jetson Orin series compatibility (sm87)
#2580 opened Feb 18, 2026 by EricEttes Loading…
5 tasks done
22
ProTip! no:milestone will show everything without a milestone.