Skip to content

Pull requests: flashinfer-ai/flashinfer

New pull request New
44 Open 963 Closed
44 Open 963 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

Update CI docker container to use latest cudnn
#1362 opened Jul 31, 2025 by yzh119 Loading…
5 tasks
4
[Draft] Update autotune results
#1361 opened Jul 31, 2025 by kaixih Loading…
5
support trtllm-gen prefill fp4 output
#1360 opened Jul 31, 2025 by weireweire Loading…
3 of 5 tasks
8
hotfix: update mxfp4 groupwise-scaled gemm unittests
#1359 opened Jul 31, 2025 by yzh119 Loading…
5 tasks
3
[fix] remove (view) transpose to keep consistent with majorness MN requirement.
#1358 opened Jul 31, 2025 by elfiegg Loading…
5 tasks
5
feature: add fp4 mm using trtllm backend
#1355 opened Jul 30, 2025 by ttyio Loading…
4 of 5 tasks
13
feat: support dynamic scale factor interface for trtllm-gen attn
#1342 opened Jul 29, 2025 by yyihuang • Draft
3 of 5 tasks
@yzh119
3
feat: Fused rope fp8 quantize kernel for MLA
#1339 opened Jul 28, 2025 by yzh119 Loading…
5 tasks
11
[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
6
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
8
Allow cudnn prefill kernels to be called natively
#1317 opened Jul 24, 2025 by Anerudhan • Draft
5 tasks done
19
[WIP] Add benchmark scripts to different moe gemms
#1315 opened Jul 24, 2025 by fzyzcjy • Draft
5 tasks
8
Wrap cudnn backend to unified interface
#1312 opened Jul 23, 2025 by cyx-6 Loading…
5 tasks
5
Api regression test for trtllmgen fp8 moe
#1308 opened Jul 23, 2025 by aleozlx Loading…
5 tasks done
7
fix: a workaround to make fp8 kv-cache work for prefill
#1304 opened Jul 22, 2025 by chenyang78 Loading…
2 tasks
19
3rparty: upgrade cutlass dependency to v4.1.0
#1299 opened Jul 22, 2025 by yzh119 Loading…
5 tasks
2
add mm_fp4 use cutlass backend for large bs
#1296 opened Jul 21, 2025 by ttyio Loading…
5 tasks done
12
ci: add github actions to upload sdist to pypi
#1270 opened Jul 16, 2025 by yzh119 Loading…
5 tasks
1
use NVSHMEM4Py instead of custom bindings for NVSHMEM MNNVL Allreduce
#1263 opened Jul 15, 2025 by Amir-19 Loading…
5 tasks
12
feat(aot): add nvshmem module for aot compilation
#1261 opened Jul 15, 2025 by EmilienM Loading…
3 of 5 tasks
1
13
refactor: separate SM100 and legacy TRT-LLM comm modules
#1259 opened Jul 15, 2025 by EmilienM Loading…
3 of 5 tasks
1
18
bugfix: fix fp32 acc threshold for qk using math::inf according to dtype by AIDC-AI
#1247 opened Jul 14, 2025 by yongchaoding Loading…
5 tasks done
5
Add the keyword "template" to member template specialization appears after . or -> in a post-fix expression which is a requirement in C++ standard
#1246 opened Jul 14, 2025 by tomflinda Loading…
9
ProTip! Filter pull requests by the default branch with base:main.