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