Yazar | SHA1 Mesaj | Tarih |
---|---|---|
AlpinDale | db73f03cdc fix: use ParallelLMHead for MLPSpeculator | 5 ay önce |
AlpinDale | 0f4a9ee77b quantized lm_head (#582) | 5 ay önce |
AlpinDale | de7e6919c0 feat: support tied weights and input scale for MLPSpeculator | 6 ay önce |
AlpinDale | 51cfadeb29 fix: `MLPSpeculator` handling of `num_speculative_tokens` | 6 ay önce |
AlpinDale | af43576da0 feat: add MLPSpeculator speculative decoding support (#572) | 6 ay önce |