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). @ 0bf916eabd712c84d5aa035803e9157899946967

AlpinDale 0bf916eabd Revert "feat: add support for chunked prefill + prefix caching (#871)"		hace 1 mes
..
block	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	hace 2 meses
__init__.py	ac1d46a2ec feat: begin work on the engine	hace 1 año
block_manager_v1.py	0bf916eabd Revert "feat: add support for chunked prefill + prefix caching (#871)"	hace 1 mes
block_manager_v2.py	0bf916eabd Revert "feat: add support for chunked prefill + prefix caching (#871)"	hace 1 mes
evictor_v1.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 5 meses
evictor_v2.py	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	hace 2 meses
interfaces.py	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	hace 2 meses
placeholder_block_space_manager.py	0bf916eabd Revert "feat: add support for chunked prefill + prefix caching (#871)"	hace 1 mes
scheduler.py	0bf916eabd Revert "feat: add support for chunked prefill + prefix caching (#871)"	hace 1 mes