Commit History

Author SHA1 Message Date
  AlpinDale 132aa2abe4 spec decode: add support for EAGLE (#899) 1 month ago
  AlpinDale 48a8693aed feat: multi-step scheduling (#831) 2 months ago
  AlpinDale bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828) 2 months ago
  Pyroserenus ee5964465d chore: max_num_seqs in throughput benchmark (#770) 3 months ago
  AlpinDale 73177656ed feat: quant_llm support (#755) 4 months ago
  AlpinDale f1d0b77c92 [0.6.0] Release Candidate (#481) 4 months ago