Skip to content

Pull requests: flashinfer-ai/flashinfer

New pull request New
63 Open 1,603 Closed
63 Open 1,603 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

Fp8 attention are now part of cuDNN 9.17.1
#2241 opened Dec 18, 2025 by Anerudhan • Draft
5 tasks done
9
agent: add CLAUDE.md and claude skills
#2240 opened Dec 18, 2025 by yzh119 Loading…
5 tasks done
41
Allreduce auto backend improvements
#2239 opened Dec 18, 2025 by nvmbreughe Loading…
3 of 5 tasks
12
fix: Handle zeros in Mistral Large 3 MoE inference
#2238 opened Dec 18, 2025 by dbari • Draft
8 of 9 tasks
4
refactor: pull trtllm-gen batch-gemm/gemm headers from artifactory; update tma descriptor shape init
#2235 opened Dec 17, 2025 by jimmyzho Loading…
5 tasks
16
feat: Fused RMSNorm + FP4 Quantization Kernels in CuTe-DSL
#2233 opened Dec 17, 2025 by bkryu Loading…
3 of 5 tasks
42
cicd / testing: Add xfails tracker script
#2227 opened Dec 16, 2025 by kahyunnam Loading…
5 tasks done
10
misc: support checks unit test tracking
#2224 opened Dec 16, 2025 by jimmyzho Loading…
5 tasks
7
chore: Update CODEOWNERS automated maintenance
#2218 opened Dec 15, 2025 by flashinfer-bot Loading…
5
feat: further optimize top-k and add fused top-k page construction kernels for DSA
#2215 opened Dec 13, 2025 by yzh119 Loading…
5 tasks done
33
WIP feat: Input/output Dump + Replay Mode for API Logging Level 10
#2206 opened Dec 11, 2025 by bkryu • Draft
3 of 5 tasks
2025 Dec
8
Fix: Add mask_indptr conversion in BatchPrefillWithPagedKVCacheWrapper.plan()
#2201 opened Dec 11, 2025 by Dutch-voyage Loading…
5 tasks
8
refactor: update fa3 codebase [part 2]
#2192 opened Dec 9, 2025 by yzh119 Loading…
4 of 5 tasks
13
Add CUDA graph buffers for persistent attention
#2185 opened Dec 7, 2025 by Edenzzzz Loading…
5 tasks
13
Fix/moe_sm110 (to be tested)
#2183 opened Dec 6, 2025 by aleozlx • Draft
5 tasks
4
[Flashinfer-Bench integration] HF end-to-end inference
#2151 opened Nov 30, 2025 by sfc-gh-goliaro • Draft
5 tasks
5
Enable Hopper FA3 FP8 attention in decode.py
#2148 opened Nov 28, 2025 by nvpohanh Loading…
5 tasks done
15
feat: support variable sequence length in decode kernel of trtllm-gen attention
#2125 opened Nov 20, 2025 by yaoyaoding Loading…
4 of 5 tasks
1
41
feat: add sink to flashinfer decode
#2087 opened Nov 13, 2025 by djmmoss Loading…
14
feat: BF16 GEMM using CUTLASS backend for SM100
#2070 opened Nov 10, 2025 by raayandhar Loading…
5 tasks done
48
Refactor flashinfer/__init__.py so that applications could selectively pack submodules without modifying __init__.py
#2027 opened Nov 3, 2025 by bangshengtang Loading…
5 tasks done
9
Blockwise GEMM with all reduce overlapping
#2007 opened Oct 30, 2025 by Amir-19 • Draft
5 tasks
1
chore: agentic workflow for automatic version bump
#1947 opened Oct 19, 2025 by yzh119 Loading…
5 tasks
35
add blockwise gemm cute dsl
#1922 opened Oct 13, 2025 by Amir-19 Loading…
5 tasks
33
Sampling non contiguous
#1916 opened Oct 12, 2025 by zcin Loading…
5 tasks done
1
8
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.