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). @ bitnet

AlpinDale 3bdeb3e116 fix: clang formatting for all kernels (#558)		hai 6 meses
..
bgmv_bf16_bf16_bf16.cu	3bdeb3e116 fix: clang formatting for all kernels (#558)	hai 6 meses
bgmv_bf16_bf16_fp16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_bf16_fp16_bf16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_bf16_fp16_fp16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_bf16_fp32_bf16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_bf16_fp32_fp16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_config.h	3bdeb3e116 fix: clang formatting for all kernels (#558)	hai 6 meses
bgmv_fp16_bf16_bf16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_fp16_bf16_fp16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_fp16_fp16_bf16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_fp16_fp16_fp16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_fp16_fp32_bf16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_fp16_fp32_fp16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_fp32_bf16_bf16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_fp32_bf16_fp16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_fp32_fp16_bf16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_fp32_fp16_fp16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_fp32_fp32_bf16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_fp32_fp32_fp16.cu	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
bgmv_impl.cuh	e3f2ea4850 make punica kernels work with rocm	hai 6 meses
generator.py	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 6 meses
vec_dtypes.cuh	e3f2ea4850 make punica kernels work with rocm	hai 6 meses