作者 | SHA1 备注 | 提交日期 |
---|---|---|
|
ac79d115b3 add guards for prefix caching, fp8, chunked, etc | 6 月之前 |
|
656459fd84 make fp8_e4m3 work on nvidia | 6 月之前 |
|
50b7c13db0 refactor: attention selector (#552) | 6 月之前 |
|
b178ae4b4a chore: generalize linear_method to be quant_method (#540) | 6 月之前 |
|
fca911ee0a vLLM Upstream Sync (#526) | 7 月之前 |