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). @ control-vectors

AlpinDale 9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale		5 maanden geleden
..
blocksparse_attention	a2d476183f fix: remove scipy and re-implement CSR matrix	5 maanden geleden
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
ipex_attn.py	9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale	5 maanden geleden
paged_attn.py	9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale	5 maanden geleden
prefix_prefill.py	d8f9f0ec16 fix: prefix prefill kernels for fp32 data type	5 maanden geleden
triton_flash_attn.py	8e11259e90 missing triton autoconfig for rocm flash attn	6 maanden geleden