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). @ prompt_logprobs_mem

50h100a bc1a2bdf98 do not use cached chunks for prompt_logprobs		il y a 3 semaines
..
block	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	il y a 1 mois
__init__.py	ac1d46a2ec feat: begin work on the engine	il y a 1 an
block_manager_v1.py	abfd4465ca feat: add support for chunked prefill + prefix caching (#871)	il y a 1 mois
block_manager_v2.py	abfd4465ca feat: add support for chunked prefill + prefix caching (#871)	il y a 1 mois
evictor_v1.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
evictor_v2.py	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	il y a 1 mois
interfaces.py	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	il y a 1 mois
placeholder_block_space_manager.py	abfd4465ca feat: add support for chunked prefill + prefix caching (#871)	il y a 1 mois
scheduler.py	bc1a2bdf98 do not use cached chunks for prompt_logprobs	il y a 3 semaines