david/aphrodite-engine

огледало од https://github.com/PygmalionAI/aphrodite-engine

Аутор	SHA1 Порука	Датум
AlpinDale	9be43994fe feat: fbgemm quantization support (#601)	пре 5 месеци
AlpinDale	00503b9fc1 feat: non-uniform quantization via `compressed-tensors` for llama	пре 5 месеци
AlpinDale	e1475fbec7 feat: MoE support with Pallas GMM kernel for TPUs	пре 6 месеци
AlpinDale	4bbf66451a chore: add CustomAP interface to UnquantizedFusedMoEMethod	пре 6 месеци
AlpinDale	1efd0f89b7 feat: support FP8 for DeepSeekV2 MoE	пре 6 месеци
AlpinDale	cf472315cc refactor: isolate FP8 from mixtral	пре 6 месеци