Commit History

Author SHA1 Message Date
  AlpinDale 4e71bd1d12 feat: add PagedAttention V2 kernels (#76) 1 year ago
  AlpinDale 24c78e7306 optimization: multi-query attention kernel 1 year ago
  AlpinDale 081545bde6 fix: various CUDA kernel tweaks 1 year ago
  AlpinDale d40a8d6bb0 chore: bind single_query_cached_kv_attention to python 1 year ago