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). @ sampler_order_string

AlpinDale 48a8693aed feat: multi-step scheduling (#831)		1 сар өмнө
..
__init__.py	04b53d2db5 chore: add initializer files	1 жил өмнө
cache_engine.py	bf88c8567e feat: mamba model support (#674)	4 сар өмнө
cpu_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 сар өмнө
cpu_worker.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 сар өмнө
embedding_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 сар өмнө
enc_dec_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 сар өмнө
model_runner.py	0a369f9171 feat: support chunked prefill with LoRA (#823)	1 сар өмнө
model_runner_base.py	48a8693aed feat: multi-step scheduling (#831)	1 сар өмнө
multi_step_model_runner.py	48a8693aed feat: multi-step scheduling (#831)	1 сар өмнө
multi_step_worker.py	48a8693aed feat: multi-step scheduling (#831)	1 сар өмнө
neuron_model_runner.py	008e646c7e chore: add support for up to 2048 block size (#715)	4 сар өмнө
neuron_worker.py	008e646c7e chore: add support for up to 2048 block size (#715)	4 сар өмнө
openvino_model_runner.py	bf88c8567e feat: mamba model support (#674)	4 сар өмнө
openvino_worker.py	bf88c8567e feat: mamba model support (#674)	4 сар өмнө
tpu_model_runner.py	81c5f196eb chore: various TPU fixes and optimizations (#746)	3 сар өмнө
tpu_worker.py	81c5f196eb chore: various TPU fixes and optimizations (#746)	3 сар өмнө
utils.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 сар өмнө
worker.py	48a8693aed feat: multi-step scheduling (#831)	1 сар өмнө
worker_base.py	48a8693aed feat: multi-step scheduling (#831)	1 сар өмнө
xpu_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 сар өмнө
xpu_worker.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө