Mook abc672e717 [Benchmark] use flashinfer bench_gpu_time instead of triton do_bench (#20305)

2026-03-12 04:04:30 +00:00

..

sglang

[Benchmark] use flashinfer bench_gpu_time instead of triton do_bench (#20305)

2026-03-12 04:04:30 +00:00

pyproject_cpu.toml

[VLM] Replace decord with torchcodec for video decoding (#20055)

2026-03-09 19:23:49 +08:00

pyproject_npu.toml

[VLM] Replace decord with torchcodec for video decoding (#20055)

2026-03-09 19:23:49 +08:00

pyproject_other.toml

[diffusion][llm] macOS support (#19549)

2026-03-10 13:11:07 -07:00

pyproject_xpu.toml

[Intel GPU] Upgrade pytorch xpu version to 2.10 (#20254)

2026-03-10 18:47:25 -07:00

pyproject.toml

bump sgl-fa4 version to 4.0.5 to loose torch deps (#20378)

2026-03-11 13:08:09 -07:00