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). @ chunked_caching_fix

AlpinDale 93bc863591 feat: Machete Kernels for Hopper GPUs (#842)		vor 1 Monat
..
aqlm	ccbda97416 fix: types in AQLM and GGUF for dynamo support (#736)	vor 3 Monaten
autoquant	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
awq	0256ed236b feat: windows support (#790)	vor 2 Monaten
compressed_tensors	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
cutlass_w8a8	a401f8e05d feat: per-tensor token epilogue kernels (#630)	vor 4 Monaten
exl2	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
fp6	73177656ed feat: quant_llm support (#755)	vor 3 Monaten
fp8	0256ed236b feat: windows support (#790)	vor 2 Monaten
gguf	ccbda97416 fix: types in AQLM and GGUF for dynamo support (#736)	vor 3 Monaten
gptq	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
gptq_marlin	f98e7b2f8c feat: add HQQ quantization support (#795)	vor 2 Monaten
int8_kvcache	9810daa699 feat: INT8 KV Cache (#298)	vor 10 Monaten
machete	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	vor 1 Monat
marlin	0256ed236b feat: windows support (#790)	vor 2 Monaten
quip	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
squeezellm	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
quant_ops.h	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	vor 1 Monat