Download Latest Version
v0.3.1 source code.tar.gz (1.6 MB)
Get an email when there's a new version of FlashInfer
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2025-08-20 | 2.1 kB | |
| v0.2.13 source code.tar.gz | 2025-08-20 | 1.5 MB | |
| v0.2.13 source code.zip | 2025-08-20 | 2.1 MB | |
| Totals: 3 Items | 3.6 MB | 0 | |
What's Changed
- test: add top_k_sampling_with_variable_k test by @JasonJ2021 in https://github.com/flashinfer-ai/flashinfer/pull/1505
- benchmark: add moe to benchmark by @nv-yunzheq in https://github.com/flashinfer-ai/flashinfer/pull/1497
- update allreduce to match trtllm by @nvjullin in https://github.com/flashinfer-ai/flashinfer/pull/1507
- Support cuda<12.8 built for trtllm_allreduce_fusion. by @strgrb in https://github.com/flashinfer-ai/flashinfer/pull/1508
- gpt-oss: Add MXFP8 x MXFP4 CUTLASS MOE for SM100 and BF16 x MXFP4 CUTLASS for SM90 + SwigluBias Activation by @djmmoss in https://github.com/flashinfer-ai/flashinfer/pull/1396
- tuner: Trtllm-gen Fp4 MoE Autotunner by @IwakuraRein in https://github.com/flashinfer-ai/flashinfer/pull/1475
- refactor fp4 masked gemm cute-dsl implementation and add manual cache by @yzh119 in https://github.com/flashinfer-ai/flashinfer/pull/1521
- fix: add missing 'requests' when building the package with AOT by @EmilienM in https://github.com/flashinfer-ai/flashinfer/pull/1517
- Fix cuda-python v13.0 import compatibility by @yongwww in https://github.com/flashinfer-ai/flashinfer/pull/1455
- misc: add license of spdlog for packaging by @yzh119 in https://github.com/flashinfer-ai/flashinfer/pull/1522
- Fix linking errors with CUDA 13 by @yongwww in https://github.com/flashinfer-ai/flashinfer/pull/1523
- release: bump version to v0.2.13 by @yongwww in https://github.com/flashinfer-ai/flashinfer/pull/1524
New Contributors
- @JasonJ2021 made their first contribution in https://github.com/flashinfer-ai/flashinfer/pull/1505
- @nv-yunzheq made their first contribution in https://github.com/flashinfer-ai/flashinfer/pull/1497
- @nvjullin made their first contribution in https://github.com/flashinfer-ai/flashinfer/pull/1507
- @strgrb made their first contribution in https://github.com/flashinfer-ai/flashinfer/pull/1508
- @djmmoss made their first contribution in https://github.com/flashinfer-ai/flashinfer/pull/1396
Full Changelog: https://github.com/flashinfer-ai/flashinfer/compare/v0.2.12...v0.2.13