david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention). @ 500f3b654fb079768f2b0d5bd0335e47e13c7f08

AlpinDale 500f3b654f fix: support bias term in compressed-tensors quant		hai 6 meses
..
__init__.py	98cb1c4cd1 feat: support fp8 via `llm-compressor`	hai 6 meses
compressed_tensors_scheme.py	500f3b654f fix: support bias term in compressed-tensors quant	hai 6 meses
compressed_tensors_unquantized.py	500f3b654f fix: support bias term in compressed-tensors quant	hai 6 meses
compressed_tensors_w4a16_24.py	500f3b654f fix: support bias term in compressed-tensors quant	hai 6 meses
compressed_tensors_w8a8_fp8.py	98cb1c4cd1 feat: support fp8 via `llm-compressor`	hai 6 meses
compressed_tensors_w8a8_int8.py	500f3b654f fix: support bias term in compressed-tensors quant	hai 6 meses
compressed_tensors_wNa16.py	500f3b654f fix: support bias term in compressed-tensors quant	hai 6 meses