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). @ 7589af22c9432c9b2148ed1ef15de97727d9cf68

Light 7589af22c9 Try to fix gguf.		il y a 8 mois
..
fused_moe	9d81716bfd [v0.5.3] Release Candidate (#388)	il y a 8 mois
ops	9181fa0396 feat: Triton kernels for sampling (#383)	il y a 9 mois
__init__.py	07aa2a492f upstream: add option to specify tokenizer	il y a 1 an
activation.py	9d81716bfd [v0.5.3] Release Candidate (#388)	il y a 8 mois
layernorm.py	e31c6f0b45 feat: refactor modeling logic and support more models (#274)	il y a 11 mois
linear.py	7589af22c9 Try to fix gguf.	il y a 8 mois
logits_processor.py	9d81716bfd [v0.5.3] Release Candidate (#388)	il y a 8 mois
rejection.py	9d81716bfd [v0.5.3] Release Candidate (#388)	il y a 8 mois
rotary_embedding.py	9d81716bfd [v0.5.3] Release Candidate (#388)	il y a 8 mois
sampler.py	9d81716bfd [v0.5.3] Release Candidate (#388)	il y a 8 mois
vocab_parallel_embedding.py	7589af22c9 Try to fix gguf.	il y a 8 mois