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). @ lm_head_lora

AlpinDale 7fffa507ff build: build flash attention kernels inside aphrodite (#1085)		1 Minggu lalu
..
blocksparse_attention	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 bulan lalu
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 bulan lalu
aphrodite_flash_attn.py	7fffa507ff build: build flash attention kernels inside aphrodite (#1085)	1 Minggu lalu
ipex_attn.py	e200775863 feat: enable using fp8 kv and prefix caching with chunked prefill (#668)	4 bulan lalu
paged_attn.py	e200775863 feat: enable using fp8 kv and prefix caching with chunked prefill (#668)	4 bulan lalu
prefix_prefill.py	e200775863 feat: enable using fp8 kv and prefix caching with chunked prefill (#668)	4 bulan lalu
triton_flash_attn.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 bulan lalu