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). @ ultravox

AlpinDale 24456206a9 fix: logit softcapping in flash-attn (#688)		vor 4 Monaten
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
abstract.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
blocksparse_attn.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
flash_attn.py	24456206a9 fix: logit softcapping in flash-attn (#688)	vor 4 Monaten
flashinfer.py	300f889554 chore: update flashinfer to v0.1.3 (#685)	vor 4 Monaten
ipex_attn.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
openvino.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
pallas.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
placeholder_attn.py	bf88c8567e feat: mamba model support (#674)	vor 4 Monaten
rocm_flash_attn.py	e200775863 feat: enable using fp8 kv and prefix caching with chunked prefill (#668)	vor 4 Monaten
torch_sdpa.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
utils.py	3bbb3f2086 feat: add numpy implementation of `compute_slot_mapping` (#678)	vor 4 Monaten
xformers.py	e200775863 feat: enable using fp8 kv and prefix caching with chunked prefill (#668)	vor 4 Monaten