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). @ 2b5af25923ebc48ba6bcfa784d97e464457e365c

AlpinDale c41462cfcd feat: exllamav2 quantization (#305)		10 сар өмнө
..
__init__.py	c41462cfcd feat: exllamav2 quantization (#305)	10 сар өмнө
aqlm.py	705821a7fe feat: AQLM quantization support (#293)	10 сар өмнө
awq.py	705821a7fe feat: AQLM quantization support (#293)	10 сар өмнө
base_config.py	c41462cfcd feat: exllamav2 quantization (#305)	10 сар өмнө
bitsandbytes.py	a98babfb74 fix: bnb on Turing GPUs (#299)	10 сар өмнө
exl2.py	c41462cfcd feat: exllamav2 quantization (#305)	10 сар өмнө
gguf.py	c41462cfcd feat: exllamav2 quantization (#305)	10 сар өмнө
gptq.py	705821a7fe feat: AQLM quantization support (#293)	10 сар өмнө
hadamard.safetensors	c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228)	11 сар өмнө
marlin.py	705821a7fe feat: AQLM quantization support (#293)	10 сар өмнө
quip.py	705821a7fe feat: AQLM quantization support (#293)	10 сар өмнө
quip_utils.py	5d288aa76c feat: add fast hadamard transformation kernels (#232)	11 сар өмнө
squeezellm.py	705821a7fe feat: AQLM quantization support (#293)	10 сар өмнө