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). @ prompt_logprobs_mem

AlpinDale 132aa2abe4 spec decode: add support for EAGLE (#899)		3 周之前
..
__init__.py	04b53d2db5 chore: add initializer files	1 年之前
cache_engine.py	bf88c8567e feat: mamba model support (#674)	4 月之前
cpu_model_runner.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 周之前
cpu_worker.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 周之前
embedding_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 月之前
enc_dec_model_runner.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 周之前
model_runner.py	132aa2abe4 spec decode: add support for EAGLE (#899)	3 周之前
model_runner_base.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 周之前
multi_step_model_runner.py	48a8693aed feat: multi-step scheduling (#831)	1 月之前
multi_step_worker.py	132aa2abe4 spec decode: add support for EAGLE (#899)	3 周之前
neuron_model_runner.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 周之前
neuron_worker.py	008e646c7e chore: add support for up to 2048 block size (#715)	3 月之前
openvino_model_runner.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 周之前
openvino_worker.py	bf88c8567e feat: mamba model support (#674)	4 月之前
tpu_model_runner.py	81c5f196eb chore: various TPU fixes and optimizations (#746)	3 月之前
tpu_worker.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 周之前
utils.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 月之前
worker.py	132aa2abe4 spec decode: add support for EAGLE (#899)	3 周之前
worker_base.py	132aa2abe4 spec decode: add support for EAGLE (#899)	3 周之前
xpu_model_runner.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 月之前
xpu_worker.py	9094a8a2a3 xpu: refactor XPU worker & executor (#861)	1 月之前