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). @ chore/test-updates

AlpinDale 6e0761ba5d make init_distributed_environment compatible with init_process_group		9 mēneši atpakaļ
..
__init__.py	04b53d2db5 chore: add initializer files	1 gadu atpakaļ
cache_engine.py	4d33ce60da feat: Triton flash attention backend for ROCm (#407)	9 mēneši atpakaļ
cpu_model_runner.py	6e0761ba5d make init_distributed_environment compatible with init_process_group	9 mēneši atpakaļ
cpu_worker.py	083ba7b452 roll back chunked prefill changes to SDPA, isolate cpu worker	9 mēneši atpakaļ
model_runner.py	8c67b37131 fix docstrings	9 mēneši atpakaļ
neuron_model_runner.py	0f1399c135 feat: attention refactor part 2	9 mēneši atpakaļ
neuron_worker.py	4d33ce60da feat: Triton flash attention backend for ROCm (#407)	9 mēneši atpakaļ
worker.py	50c2434267 move megatron to a top-level directory	9 mēneši atpakaļ
worker_base.py	8c67b37131 fix docstrings	9 mēneši atpakaļ