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). @ ed6717d0c064a1cbf0fe9f358008ffc43e20187a

AlpinDale ba371fbbbd feat: AWQ marlin kernels (#603)		vor 5 Monaten
..
__init__.py	98cb1c4cd1 feat: support fp8 via `llm-compressor`	vor 5 Monaten
compressed_tensors_scheme.py	19340b672e chore: improve min_capability checking for `compressed-tensors`	vor 5 Monaten
compressed_tensors_unquantized.py	00503b9fc1 feat: non-uniform quantization via `compressed-tensors` for llama	vor 5 Monaten
compressed_tensors_w4a16_24.py	19340b672e chore: improve min_capability checking for `compressed-tensors`	vor 5 Monaten
compressed_tensors_w8a8_fp8.py	d3c474d219 chore: enable dynamic per-token `fp8`	vor 5 Monaten
compressed_tensors_w8a8_int8.py	19340b672e chore: improve min_capability checking for `compressed-tensors`	vor 5 Monaten
compressed_tensors_wNa16.py	ba371fbbbd feat: AWQ marlin kernels (#603)	vor 5 Monaten