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). @ ee174ea4fd3bda4f206c74e0c3f53d978fb10475

AlpinDale c8c6de64cd fix: typo in pallas backend		7 mesi fa
..
backends	c8c6de64cd fix: typo in pallas backend	7 mesi fa
ops	805fa8721d feat: use intel_extension_for_pytorch for CPU backend	7 mesi fa
__init__.py	a94de94c44 refactor: combine the prefill and decode into a single API (#553)	7 mesi fa
layer.py	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	7 mesi fa
selector.py	a524667db0 fix: device assertion for sdpa backend; fix env for tpu worker	7 mesi fa