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). @ b9b5e352cb3d01a6fdb678441d587925d95ec343

AlpinDale 6144150398 chore: use scalar type to dispatch to different `gptq_marlin` kernels (#689)		hai 4 meses
..
aqlm	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses
autoquant	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses
awq	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses
compressed_tensors	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses
cutlass_w8a8	a401f8e05d feat: per-tensor token epilogue kernels (#630)	hai 4 meses
exl2	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses
fp8	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses
gguf	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses
gptq	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses
gptq_marlin	6144150398 chore: use scalar type to dispatch to different `gptq_marlin` kernels (#689)	hai 4 meses
int8_kvcache	9810daa699 feat: INT8 KV Cache (#298)	hai 10 meses
marlin	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses
quip	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses
squeezellm	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses
quant_ops.h	a401f8e05d feat: per-tensor token epilogue kernels (#630)	hai 4 meses