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). @ control-vectors

AlpinDale 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)		il y a 5 mois
..
autogptq_cuda_256.cpp	801eda0b7a feat: support GPTQ 2, 3, and 8bit quants (#181)	il y a 1 an
autogptq_cuda_64.cpp	801eda0b7a feat: support GPTQ 2, 3, and 8bit quants (#181)	il y a 1 an
autogptq_cuda_kernel_256.cu	801eda0b7a feat: support GPTQ 2, 3, and 8bit quants (#181)	il y a 1 an
autogptq_cuda_kernel_64.cu	801eda0b7a feat: support GPTQ 2, 3, and 8bit quants (#181)	il y a 1 an
compat.cuh	2755a48d51 merge dev branch into main (#153)	il y a 1 an
matrix_view.cuh	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	il y a 11 mois
q_gemm.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	il y a 5 mois
qdq_2.cuh	801eda0b7a feat: support GPTQ 2, 3, and 8bit quants (#181)	il y a 1 an
qdq_3.cuh	801eda0b7a feat: support GPTQ 2, 3, and 8bit quants (#181)	il y a 1 an
qdq_4.cuh	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	il y a 11 mois
qdq_8.cuh	801eda0b7a feat: support GPTQ 2, 3, and 8bit quants (#181)	il y a 1 an
qdq_util.cuh	2755a48d51 merge dev branch into main (#153)	il y a 1 an