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). @ sampling-kernels

AlpinDale ba371fbbbd feat: AWQ marlin kernels (#603)		пре 4 месеци
..
__init__.py	98cb1c4cd1 feat: support fp8 via `llm-compressor`	пре 4 месеци
marlin_utils.py	ba371fbbbd feat: AWQ marlin kernels (#603)	пре 4 месеци
marlin_utils_fp8.py	055963b252 fix: channel-wise fp8 marlin	пре 4 месеци
marlin_utils_test.py	ba371fbbbd feat: AWQ marlin kernels (#603)	пре 4 месеци
marlin_utils_test_24.py	058e629f8e chore: refactor marlin python utils	пре 4 месеци
quant_utils.py	ba371fbbbd feat: AWQ marlin kernels (#603)	пре 4 месеци
w8a8_utils.py	5d98b7ead1 fix: input_scale for w8a8 is optional	пре 4 месеци