Autor | SHA1 Nachricht | Datum |
---|---|---|
|
d34e083c48 feat: add experts_int8 support (#730) | vor 4 Monaten |
|
b0f262eec1 feat: FP8 quantization support for AMD ROCm (#729) | vor 4 Monaten |
|
4ec08af18b chore: update fused MoE weight loading (#700) | vor 5 Monaten |
|
f1d0b77c92 [0.6.0] Release Candidate (#481) | vor 5 Monaten |