david/aphrodite-engine

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

Аутор	SHA1 Порука	Датум
AlpinDale	00503b9fc1 feat: non-uniform quantization via `compressed-tensors` for llama	пре 5 месеци
AlpinDale	ee2c5d34da feat: add fp8 channel-wise weight quantization support	пре 5 месеци
AlpinDale	98cb1c4cd1 feat: support fp8 via `llm-compressor`	пре 5 месеци
AlpinDale	e2dbe5f05c feat: add sparse marlin for compressed tensors	пре 5 месеци
AlpinDale	aba03b4756 feat: dynamic per-token activation quantization	пре 5 месеци