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).

AlpinDale 9c9b2dd843 core: improve warmup times for prefix caching in block manager v2 (#920)		3 weeks ago
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 months ago
block_table.py	79d603954e fix: chunked prefill with v2 block manager (#679)	3 months ago
common.py	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	1 month ago
cpu_gpu_block_allocator.py	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	1 month ago
interfaces.py	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	1 month ago
naive_block.py	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	1 month ago
prefix_caching_block.py	9c9b2dd843 core: improve warmup times for prefix caching in block manager v2 (#920)	3 weeks ago
utils.py	a0e446a17d feat: initial encoder-decoder support with BART model (#633)	4 months ago