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). @ feat/tree-attention

AlpinDale c577c31aaa feat: tree attention		9 hónapja
..
__init__.py	04b53d2db5 chore: add initializer files	1 éve
cache_engine.py	4d33ce60da feat: Triton flash attention backend for ROCm (#407)	9 hónapja
cpu_model_runner.py	6e0761ba5d make init_distributed_environment compatible with init_process_group	9 hónapja
cpu_worker.py	d8c4193704 feat: Speculative Decoding using a draft model (#432)	9 hónapja
model_runner.py	c577c31aaa feat: tree attention	9 hónapja
neuron_model_runner.py	0f1399c135 feat: attention refactor part 2	9 hónapja
neuron_worker.py	d8c4193704 feat: Speculative Decoding using a draft model (#432)	9 hónapja
worker.py	d8c4193704 feat: Speculative Decoding using a draft model (#432)	9 hónapja
worker_base.py	d8c4193704 feat: Speculative Decoding using a draft model (#432)	9 hónapja