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). @ 058e629f8e26c83b4bc839fac444c66734975ba5

AlpinDale 058e629f8e chore: refactor marlin python utils		6 ماه پیش
..
__init__.py	98cb1c4cd1 feat: support fp8 via `llm-compressor`	6 ماه پیش
marlin_utils.py	058e629f8e chore: refactor marlin python utils	6 ماه پیش
marlin_utils_fp8.py	058e629f8e chore: refactor marlin python utils	6 ماه پیش
marlin_utils_test.py	058e629f8e chore: refactor marlin python utils	6 ماه پیش
marlin_utils_test_24.py	058e629f8e chore: refactor marlin python utils	6 ماه پیش
quant_utils.py	98cb1c4cd1 feat: support fp8 via `llm-compressor`	6 ماه پیش
w8a8_utils.py	98cb1c4cd1 feat: support fp8 via `llm-compressor`	6 ماه پیش