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). @ ad1c6b86a1fa85e28c0a3e177a46f481d0cc4642

AlpinDale fca911ee0a vLLM Upstream Sync (#526)		8 сар өмнө
..
common.h	e0c35bb353 feat: bitsandbytes and `--load-in{4,8}bit` support (#294)	1 жил өмнө
cta_iterator.h	e0c35bb353 feat: bitsandbytes and `--load-in{4,8}bit` support (#294)	1 жил өмнө
format.cu	a98babfb74 fix: bnb on Turing GPUs (#299)	1 жил өмнө
format.h	fca911ee0a vLLM Upstream Sync (#526)	8 сар өмнө
gemm_s4_f16.cu	a98babfb74 fix: bnb on Turing GPUs (#299)	1 жил өмнө
gemm_s4_f16.h	e0c35bb353 feat: bitsandbytes and `--load-in{4,8}bit` support (#294)	1 жил өмнө
gemm_s4_f16_kernel.h	e0c35bb353 feat: bitsandbytes and `--load-in{4,8}bit` support (#294)	1 жил өмнө
gemm_template.h	e0c35bb353 feat: bitsandbytes and `--load-in{4,8}bit` support (#294)	1 жил өмнө
int4_fp16_gemm_kernels.cu	a98babfb74 fix: bnb on Turing GPUs (#299)	1 жил өмнө
metric.h	e0c35bb353 feat: bitsandbytes and `--load-in{4,8}bit` support (#294)	1 жил өмнө
warp_iterator.h	e0c35bb353 feat: bitsandbytes and `--load-in{4,8}bit` support (#294)	1 жил өмнө