Autor | SHA1 Nachricht | Datum |
---|---|---|
|
22422d962b feat: add cuda sampling kernels for top_k and top_p | vor 2 Monaten |
|
ee5964465d chore: max_num_seqs in throughput benchmark (#770) | vor 4 Monaten |
|
73177656ed feat: quant_llm support (#755) | vor 4 Monaten |
|
f1d0b77c92 [0.6.0] Release Candidate (#481) | vor 5 Monaten |