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). @ video

AlpinDale dcebb8487d video modality support		3 veckor sedan
..
__init__.py	04b53d2db5 chore: add initializer files	1 år sedan
cache_engine.py	bf88c8567e feat: mamba model support (#674)	4 månader sedan
cpu_model_runner.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 veckor sedan
cpu_worker.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 veckor sedan
embedding_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 månader sedan
enc_dec_model_runner.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 veckor sedan
model_runner.py	dcebb8487d video modality support	3 veckor sedan
model_runner_base.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 veckor sedan
multi_step_model_runner.py	48a8693aed feat: multi-step scheduling (#831)	1 månad sedan
multi_step_worker.py	48a8693aed feat: multi-step scheduling (#831)	1 månad sedan
neuron_model_runner.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 veckor sedan
neuron_worker.py	008e646c7e chore: add support for up to 2048 block size (#715)	3 månader sedan
openvino_model_runner.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 veckor sedan
openvino_worker.py	bf88c8567e feat: mamba model support (#674)	4 månader sedan
tpu_model_runner.py	81c5f196eb chore: various TPU fixes and optimizations (#746)	3 månader sedan
tpu_worker.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 veckor sedan
utils.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 månader sedan
worker.py	48a8693aed feat: multi-step scheduling (#831)	1 månad sedan
worker_base.py	48a8693aed feat: multi-step scheduling (#831)	1 månad sedan
xpu_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 månader sedan
xpu_worker.py	9094a8a2a3 xpu: refactor XPU worker & executor (#861)	1 månad sedan