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). @ c577c31aaa69eb5b4768b491b54dc407a7d2bbe4

AlpinDale 8d26cf3876 simplify model_executor logic		hai 9 meses
..
__init__.py	bd0ddf1cfe feat: EETQ quantization (#408)	hai 9 meses
aqlm.py	41beab5dc1 add exllamav2 tensor paralell, fused MoE for GPTQ/AWQ	hai 10 meses
awq.py	41beab5dc1 add exllamav2 tensor paralell, fused MoE for GPTQ/AWQ	hai 10 meses
base_config.py	aa244761ed formatting and typing	hai 10 meses
bitsandbytes.py	fa083286e3 Speculative Decoding Part 4: Lookahead scheduling (#402)	hai 9 meses
eetq.py	8d26cf3876 simplify model_executor logic	hai 9 meses
exl2.py	ea26c91e52 proper typing	hai 10 meses
gguf.py	ea26c91e52 proper typing	hai 10 meses
gptq.py	41beab5dc1 add exllamav2 tensor paralell, fused MoE for GPTQ/AWQ	hai 10 meses
hadamard.safetensors	c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228)	hai 1 ano
marlin.py	ea26c91e52 proper typing	hai 10 meses
quip.py	ea26c91e52 proper typing	hai 10 meses
quip_utils.py	e42a78381a feat: switch from pylint to ruff (#322)	hai 10 meses
schema.py	7528e0ce3e make detokenization optional	hai 9 meses
squeezellm.py	ea26c91e52 proper typing	hai 10 meses