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). @ rep_pen_range

AlpinDale 89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)		3 달 전
..
__init__.py	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	9 달 전
cpu_executor.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 달 전
distributed_gpu_executor.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 달 전
executor_base.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 달 전
gpu_executor.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 달 전
multiproc_gpu_executor.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 달 전
multiproc_worker_utils.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 달 전
neuron_executor.py	008e646c7e chore: add support for up to 2048 block size (#715)	3 달 전
openvino_executor.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 달 전
ray_gpu_executor.py	7debd35ca2 fix: shut down ray dag workers cleanly (#692)	4 달 전
ray_tpu_executor.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 달 전
ray_utils.py	5d37ec1016 suppress tpu import warning (#696)	4 달 전
ray_xpu_executor.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 달 전
tpu_executor.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 달 전
xpu_executor.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	3 달 전