Skip to content

Pull requests: flashinfer-ai/flashinfer

New pull request New
67 Open 1,648 Closed
67 Open 1,648 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

feat: add batch_invariant option to trtllm decode functions
#2321 opened Jan 9, 2026 by yzh119 Loading…
1
14
Fix filtered topk unified kernel
#2319 opened Jan 9, 2026 by murphymatt Loading…
5 tasks done
9
tiny support glm routing
#2313 opened Jan 8, 2026 by b8zhong Loading…
1
6
refactor: decorate all operators with @flashinfer_api
#2311 opened Jan 8, 2026 by bkryu Loading…
1
21
Fix: FilteredTopKUnifiedKernel read value out of length
#2308 opened Jan 8, 2026 by HarryWu99 Loading…
4 tasks done
11
Fused MoE non gated Relu2 FP8
#2304 opened Jan 7, 2026 by amitz-nv • Draft
5 tasks
9
[Perf][Feature] Add SM103-specific schedulers for NVFP4 CUTLASS kernels
#2303 opened Jan 7, 2026 by LopezCastroRoberto Loading…
12
Selective State Update kernel (mamba)
#2301 opened Jan 6, 2026 by ishovkun Loading…
5 tasks done
57
Restructure README with updated features, GPU support table, and clearer organization
#2298 opened Jan 6, 2026 by sricketts Loading…
3 tasks done
22
chore: Update XFails Report automated maintenance testing
#2287 opened Jan 5, 2026 by flashinfer-bot Loading…
4
chore: Update CODEOWNERS automated maintenance
#2286 opened Jan 5, 2026 by flashinfer-bot Loading…
2
feat: Add FP8/NVFP4 quant fusion for MNNVL Allreduce
#2263 opened Dec 24, 2025 by timlee0212 • Draft
5 tasks
12
chore: add __all__ exports to Python modules and document missing APIs
#2251 opened Dec 20, 2025 by yzh119 Loading…
5 tasks
14
bugfix: skip CUTLASS kernel generation when AOT cache exists
#2248 opened Dec 19, 2025 by yongwww Loading…
3 of 5 tasks
1
7
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
misc: support checks unit test tracking
#2224 opened Dec 16, 2025 by jimmyzho Loading…
5 tasks
10
feat: Input/output Dump + Replay Mode for API Logging Level 10
#2206 opened Dec 11, 2025 by bkryu Loading…
3 of 5 tasks
@bkryu
34
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
15
Add CUDA graph buffers for persistent attention
#2185 opened Dec 7, 2025 by Edenzzzz Loading…
5 tasks
13
[Flashinfer-Bench integration] HF end-to-end inference
#2151 opened Nov 30, 2025 by sfc-gh-goliaro • Draft
5 tasks
5
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
97
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
ProTip! Filter pull requests by the default branch with base:main.