作者 | SHA1 備註 | 提交日期 |
---|---|---|
|
22422d962b feat: add cuda sampling kernels for top_k and top_p | 2 月之前 |
|
ee5964465d chore: max_num_seqs in throughput benchmark (#770) | 4 月之前 |
|
73177656ed feat: quant_llm support (#755) | 4 月之前 |
|
f1d0b77c92 [0.6.0] Release Candidate (#481) | 5 月之前 |