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). @ no_dry_seqs

AlpinDale 48a8693aed feat: multi-step scheduling (#831)		hai 2 meses
..
__init__.py	04b53d2db5 chore: add initializer files	hai 1 ano
cache_engine.py	bf88c8567e feat: mamba model support (#674)	hai 4 meses
cpu_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	hai 4 meses
cpu_worker.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	hai 4 meses
embedding_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	hai 4 meses
enc_dec_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	hai 4 meses
model_runner.py	0a369f9171 feat: support chunked prefill with LoRA (#823)	hai 2 meses
model_runner_base.py	48a8693aed feat: multi-step scheduling (#831)	hai 2 meses
multi_step_model_runner.py	48a8693aed feat: multi-step scheduling (#831)	hai 2 meses
multi_step_worker.py	48a8693aed feat: multi-step scheduling (#831)	hai 2 meses
neuron_model_runner.py	008e646c7e chore: add support for up to 2048 block size (#715)	hai 4 meses
neuron_worker.py	008e646c7e chore: add support for up to 2048 block size (#715)	hai 4 meses
openvino_model_runner.py	bf88c8567e feat: mamba model support (#674)	hai 4 meses
openvino_worker.py	bf88c8567e feat: mamba model support (#674)	hai 4 meses
tpu_model_runner.py	81c5f196eb chore: various TPU fixes and optimizations (#746)	hai 4 meses
tpu_worker.py	81c5f196eb chore: various TPU fixes and optimizations (#746)	hai 4 meses
utils.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	hai 4 meses
worker.py	48a8693aed feat: multi-step scheduling (#831)	hai 2 meses
worker_base.py	48a8693aed feat: multi-step scheduling (#831)	hai 2 meses
xpu_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	hai 4 meses
xpu_worker.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses