Commit History

Author SHA1 Message Date
  AlpinDale ba371fbbbd feat: AWQ marlin kernels (#603) 4 months ago
  AlpinDale fa15bad2ea chore: minor AMD fixes 4 months ago
  AlpinDale dd18c5042c move prepare_inputs to the GPU (#596) 4 months ago
  AlpinDale f5d52320da Port mamba kernels to Aphrodite (#595) 4 months ago
  AlpinDale 321a0892e0 let's not build these for now 4 months ago
  AlpinDale b1e61268a8 bump torch to 2.3.1 4 months ago
  AlpinDale ddb28a80a3 fix: bump torch for rocm, unify CUDA_VISIBLE_DEVICES for cuda and rocm 4 months ago
  AlpinDale ad24e74a99 feat: FP8 weight-only quantization support for Ampere GPUs 4 months ago
  AlpinDale 5be90c3859 Mamba infrastrucuture support (#586) 4 months ago
  AlpinDale 5b464d36ea feat: bias epilogue support for cutlass kernels 5 months ago
  AlpinDale 2c321ce1f2 chore: upgrade to rocm 6.1, update docker 5 months ago
  AlpinDale 7e54c3916d chore: factor out epilogues from cutlass kernels 5 months ago
  AlpinDale 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 5 months ago
  AlpinDale 00acf371f9 rocm: fused topk softmax 5 months ago
  AlpinDale 0307da9e15 refactor: bitsandbytes -> autoquant 5 months ago
  AlpinDale 4ab4c5c87c oops 5 months ago
  AlpinDale d45c846c8c do not build sm_90a for cuda 11 5 months ago
  AlpinDale f4ea11b982 feat: initial support for activation quantization 5 months ago
  AlpinDale 2313c97e3d add cutlass w8a8 kernels (#556) 5 months ago
  AlpinDale c66b1b57b1 Marlin 2:4 sparsity (#555) 5 months ago
  AlpinDale 251568470e initial nvidia fp8 e4m3 for kv cache 5 months ago
  AlpinDale e3f2ea4850 make punica kernels work with rocm 5 months ago
  AlpinDale f22b700ee4 feat: marlin kernels for GPTQ (#547) 5 months ago
  AlpinDale fca911ee0a vLLM Upstream Sync (#526) 6 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