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). @ 3f92035bf1bdb4de1882b03d994c114b4aeb6ea4

AlpinDale 3f92035bf1 fix: add `ignored_seq_groups` in `_schedule_chunked_prefill`		7 hónapja
..
block	237fa59aea feat: support CPU/GPU swapping in BlockManagerV2	7 hónapja
__init__.py	ac1d46a2ec feat: begin work on the engine	1 éve
block_manager_v1.py	237fa59aea feat: support CPU/GPU swapping in BlockManagerV2	7 hónapja
block_manager_v2.py	237fa59aea feat: support CPU/GPU swapping in BlockManagerV2	7 hónapja
embedding_model_block_manager.py	237fa59aea feat: support CPU/GPU swapping in BlockManagerV2	7 hónapja
evictor_v1.py	5fecc6b025 when was this deprecated?	7 hónapja
evictor_v2.py	5fecc6b025 when was this deprecated?	7 hónapja
interfaces.py	237fa59aea feat: support CPU/GPU swapping in BlockManagerV2	7 hónapja
policy.py	fca911ee0a vLLM Upstream Sync (#526)	8 hónapja
scheduler.py	3f92035bf1 fix: add `ignored_seq_groups` in `_schedule_chunked_prefill`	7 hónapja