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). @ feat/perplexity

AlpinDale a98babfb74 fix: bnb on Turing GPUs (#299)		10 kuukautta sitten
..
common.h	e0c35bb353 feat: bitsandbytes and `--load-in{4,8}bit` support (#294)	10 kuukautta sitten
cta_iterator.h	e0c35bb353 feat: bitsandbytes and `--load-in{4,8}bit` support (#294)	10 kuukautta sitten
format.cu	a98babfb74 fix: bnb on Turing GPUs (#299)	10 kuukautta sitten
format.h	e0c35bb353 feat: bitsandbytes and `--load-in{4,8}bit` support (#294)	10 kuukautta sitten
gemm_s4_f16.cu	a98babfb74 fix: bnb on Turing GPUs (#299)	10 kuukautta sitten
gemm_s4_f16.h	e0c35bb353 feat: bitsandbytes and `--load-in{4,8}bit` support (#294)	10 kuukautta sitten
gemm_s4_f16_kernel.h	e0c35bb353 feat: bitsandbytes and `--load-in{4,8}bit` support (#294)	10 kuukautta sitten
gemm_template.h	e0c35bb353 feat: bitsandbytes and `--load-in{4,8}bit` support (#294)	10 kuukautta sitten
int4_fp16_gemm_kernels.cu	a98babfb74 fix: bnb on Turing GPUs (#299)	10 kuukautta sitten
metric.h	e0c35bb353 feat: bitsandbytes and `--load-in{4,8}bit` support (#294)	10 kuukautta sitten
warp_iterator.h	e0c35bb353 feat: bitsandbytes and `--load-in{4,8}bit` support (#294)	10 kuukautta sitten