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). @ fp8-quant

AlpinDale c20073824a cleanup		7 maanden geleden
..
gguf_utils	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
__init__.py	85a865cc00 feat: fp8 quant	7 maanden geleden
aqlm.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
awq.py	483c95a2f8 fix ops in gptq and awq	7 maanden geleden
base_config.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
bitsandbytes.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
eetq.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
exl2.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
fp8.py	c20073824a cleanup	7 maanden geleden
gguf.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
gptq.py	483c95a2f8 fix ops in gptq and awq	7 maanden geleden
hadamard.safetensors	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
marlin.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
quip.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
quip_utils.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
schema.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
squeezellm.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden