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). @ uneven-head-size-flashinfer

AlpinDale abfd4465ca feat: add support for chunked prefill + prefix caching (#871)		vor 1 Monat
..
__init__.py	04b53d2db5 chore: add initializer files	vor 1 Jahr
cache_engine.py	bf88c8567e feat: mamba model support (#674)	vor 4 Monaten
cpu_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	vor 3 Monaten
cpu_worker.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	vor 3 Monaten
embedding_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	vor 3 Monaten
enc_dec_model_runner.py	1405051912 attention: add `AttentionState` abstraction (#863)	vor 1 Monat
model_runner.py	abfd4465ca feat: add support for chunked prefill + prefix caching (#871)	vor 1 Monat
model_runner_base.py	48a8693aed feat: multi-step scheduling (#831)	vor 1 Monat
multi_step_model_runner.py	48a8693aed feat: multi-step scheduling (#831)	vor 1 Monat
multi_step_worker.py	48a8693aed feat: multi-step scheduling (#831)	vor 1 Monat
neuron_model_runner.py	008e646c7e chore: add support for up to 2048 block size (#715)	vor 3 Monaten
neuron_worker.py	008e646c7e chore: add support for up to 2048 block size (#715)	vor 3 Monaten
openvino_model_runner.py	bf88c8567e feat: mamba model support (#674)	vor 4 Monaten
openvino_worker.py	bf88c8567e feat: mamba model support (#674)	vor 4 Monaten
tpu_model_runner.py	81c5f196eb chore: various TPU fixes and optimizations (#746)	vor 3 Monaten
tpu_worker.py	81c5f196eb chore: various TPU fixes and optimizations (#746)	vor 3 Monaten
utils.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	vor 3 Monaten
worker.py	48a8693aed feat: multi-step scheduling (#831)	vor 1 Monat
worker_base.py	48a8693aed feat: multi-step scheduling (#831)	vor 1 Monat
xpu_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	vor 3 Monaten
xpu_worker.py	9094a8a2a3 xpu: refactor XPU worker & executor (#861)	vor 1 Monat