| .. |
|
__init__.py
|
04b53d2db5
chore: add initializer files
|
1 year ago |
|
cache_engine.py
|
5289c14b24
feat: Asymmetric Tensor Parallel (#594)
|
4 months ago |
|
cpu_model_runner.py
|
99680b2d23
feat: soft prompts (#589)
|
4 months ago |
|
cpu_worker.py
|
99680b2d23
feat: soft prompts (#589)
|
4 months ago |
|
embedding_model_runner.py
|
5289c14b24
feat: Asymmetric Tensor Parallel (#594)
|
4 months ago |
|
model_runner.py
|
6671e3a162
feat: add CPU offloading support (#598)
|
4 months ago |
|
model_runner_base.py
|
a3e26391e4
chore: add a wrapper for torch.inference_mode decorator
|
4 months ago |
|
neuron_model_runner.py
|
4599c98f99
feat: dynamic image size support for VLMs
|
4 months ago |
|
neuron_worker.py
|
ae04f57ec1
feat: Pipeline Parallel support (#581)
|
4 months ago |
|
openvino_model_runner.py
|
4f7d212b70
feat: remove vision language config
|
4 months ago |
|
openvino_worker.py
|
1ff6d4c3d7
feat: support pipeline parallel on indivisible GPU count (#587)
|
4 months ago |
|
tpu_model_runner.py
|
f91991f584
fix: f-string fixes
|
4 months ago |
|
tpu_worker.py
|
b6c4dfce23
chore: refactor TPU model runner and worker
|
4 months ago |
|
worker.py
|
e8af0d4a3b
fix: type annotation in worker
|
4 months ago |
|
worker_base.py
|
a3e26391e4
chore: add a wrapper for torch.inference_mode decorator
|
4 months ago |
|
xpu_model_runner.py
|
99680b2d23
feat: soft prompts (#589)
|
4 months ago |
|
xpu_worker.py
|
99680b2d23
feat: soft prompts (#589)
|
4 months ago |
AlpinDale
f91991f584
fix: f-string fixes