Download Latest Version
Release v0.2.11.post3 source code.tar.gz (1.4 MB)
Get an email when there's a new version of FlashInfer
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2025-08-13 | 2.5 kB | |
| v0.2.11.post2 source code.tar.gz | 2025-08-13 | 1.4 MB | |
| v0.2.11.post2 source code.zip | 2025-08-13 | 2.0 MB | |
| Totals: 3 Items | 3.4 MB | 0 | |
What's Changed
- [doc]: Update installation doc and readme by @yongwww in https://github.com/flashinfer-ai/flashinfer/pull/1465
- Allow BatchPrefillPagedWrapper to call cudnn API by @Anerudhan in https://github.com/flashinfer-ai/flashinfer/pull/1384
- [RFC] log filename and lineno in flashinfer jit logger by @842974287 in https://github.com/flashinfer-ai/flashinfer/pull/1461
- Add Mxfp4 trtllm-gen moe unit tests by @IwakuraRein in https://github.com/flashinfer-ai/flashinfer/pull/1399
- bugfix: Verify num_experts greater or equal to local_experts + offset by @amirkl94 in https://github.com/flashinfer-ai/flashinfer/pull/1469
- [RFC] add an env to allow specify cubins directory by @842974287 in https://github.com/flashinfer-ai/flashinfer/pull/1462
- Fix "more than one operator "/" matches these operands" by @842974287 in https://github.com/flashinfer-ai/flashinfer/pull/1471
- Fix race condition when JitSpec loads the library by @nvpohanh in https://github.com/flashinfer-ai/flashinfer/pull/1467
- perf: add 1x4x1 cluster shape for fp8 bmm M<16 cases by @ttyio in https://github.com/flashinfer-ai/flashinfer/pull/1473
- feat: Enable multiple fused-moe backends by @amirkl94 in https://github.com/flashinfer-ai/flashinfer/pull/1472
- Remove restrict extension to fix compilation error on GB200 by @842974287 in https://github.com/flashinfer-ai/flashinfer/pull/1470
- feat: masked layout fp4 gemm using cute-dsl by @yzh119 in https://github.com/flashinfer-ai/flashinfer/pull/1331
- fix: minor fix after [#1384] by @yyihuang in https://github.com/flashinfer-ai/flashinfer/pull/1476
- fix: remove redundant zero_init reverted by [#1459] by @yyihuang in https://github.com/flashinfer-ai/flashinfer/pull/1463
- Remove getEnvEnablePDL in favor of enable_pdl parameter by @yongwww in https://github.com/flashinfer-ai/flashinfer/pull/1446
- Unify and modularize decode and prefill test. by @weireweire in https://github.com/flashinfer-ai/flashinfer/pull/1375
- refactor: Improved metainfo for trtllm-gen kernels by @cyx-6 in https://github.com/flashinfer-ai/flashinfer/pull/1328
- Tone down the amount of logging when downloading cubins by @joker-eph in https://github.com/flashinfer-ai/flashinfer/pull/1477
- release: bump version to v0.2.11.post2 by @yyihuang in https://github.com/flashinfer-ai/flashinfer/pull/1478
Full Changelog: https://github.com/flashinfer-ai/flashinfer/compare/v0.2.11.post1...v0.2.11.post2