Commit History

Author SHA1 Message Date
  AlpinDale 4a7cb8f232 rocm: add custom paged attention kernels for ROCm (#1043) 1 week ago
  AlpinDale 51d24fc7c0 build: shallow clone cutlass 3.5.1 tag (#1010) 1 week ago
  AlpinDale 313e198557 api: implement OpenAI-compatible tools API for Hermes/Mistral models (#993) 2 weeks ago
  AlpinDale 9f3e7c86e2 feat: add fused Marlin MoE kernel (#934) 2 weeks ago
  AlpinDale 2a60b8f8c9 kernel: do not compile machete for cuda 11 and below (#901) 3 weeks ago
  AlpinDale afadef06cd build: pass `PYTHONPATH` from setup.py to cmake (#879) 3 weeks ago
  Naomiusearch 4f9fea4c4d fix: ROCm build (#817) 1 month ago
  AlpinDale 93bc863591 feat: Machete Kernels for Hopper GPUs (#842) 1 month ago
  AlpinDale bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828) 1 month ago
  AlpinDale 0256ed236b feat: windows support (#790) 2 months ago
  Naomiusearch eee3cf5dab fix: make AMD usable (#775) 2 months ago
  AlpinDale 73177656ed feat: quant_llm support (#755) 3 months ago
  AlpinDale ec32f999bc build: bump cmake to 3.26 (#691) 3 months ago
  AlpinDale f1d0b77c92 [0.6.0] Release Candidate (#481) 4 months ago
  AlpinDale 9d81716bfd [v0.5.3] Release Candidate (#388) 8 months ago
  AlpinDale e120404436 Revert "feat: CMake Build System Generator (#332)" 9 months ago
  AlpinDale ad6802690f feat: CMake Build System Generator (#332) 9 months ago