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). @ deepseek_v3

AlpinDale f1d0b77c92 [0.6.0] Release Candidate (#481)		hai 4 meses
..
autogptq_cuda_256.cpp	801eda0b7a feat: support GPTQ 2, 3, and 8bit quants (#181)	hai 1 ano
autogptq_cuda_64.cpp	801eda0b7a feat: support GPTQ 2, 3, and 8bit quants (#181)	hai 1 ano
autogptq_cuda_kernel_256.cu	801eda0b7a feat: support GPTQ 2, 3, and 8bit quants (#181)	hai 1 ano
autogptq_cuda_kernel_64.cu	801eda0b7a feat: support GPTQ 2, 3, and 8bit quants (#181)	hai 1 ano
compat.cuh	2755a48d51 merge dev branch into main (#153)	hai 1 ano
matrix_view.cuh	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	hai 11 meses
q_gemm.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses
qdq_2.cuh	801eda0b7a feat: support GPTQ 2, 3, and 8bit quants (#181)	hai 1 ano
qdq_3.cuh	801eda0b7a feat: support GPTQ 2, 3, and 8bit quants (#181)	hai 1 ano
qdq_4.cuh	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	hai 11 meses
qdq_8.cuh	801eda0b7a feat: support GPTQ 2, 3, and 8bit quants (#181)	hai 1 ano
qdq_util.cuh	2755a48d51 merge dev branch into main (#153)	hai 1 ano