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). @ c2be1b9f29d884610a42832fe3b643e3152163ff

AlpinDale aed64884c6 feat: prompt logprobs with chunked prefill (#539)		5 months ago
..
block	46159b107a formatting: pt1	6 months ago
__init__.py	ac1d46a2ec feat: begin work on the engine	1 year ago
block_manager_v1.py	fca911ee0a vLLM Upstream Sync (#526)	6 months ago
block_manager_v2.py	fca911ee0a vLLM Upstream Sync (#526)	6 months ago
evictor.py	375f24ccca fix: optimize context shift performance (#380)	9 months ago
interfaces.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 months ago
policy.py	fca911ee0a vLLM Upstream Sync (#526)	6 months ago
scheduler.py	aed64884c6 feat: prompt logprobs with chunked prefill (#539)	5 months ago