Hongxia Yangandlcskrishna 05af6da8d9 [ROCm] enable cupy in order to enable cudagraph mode for AMD GPUs (#3123) ...

Co-authored-by: lcskrishna <lollachaitanya@gmail.com>

2024-03-04 18:14:53 -08:00

..

spec_decode

Push logprob generation to LLMEngine (#3065)

2024-03-04 19:54:06 +00:00

__init__.py

Change the name to vLLM (#150)

2023-06-17 03:07:40 -07:00

cache_engine.py

[Neuron] Support inference with transformers-neuronx (#2569)

2024-02-28 09:34:34 -08:00

model_runner.py

Add Automatic Prefix Caching (#2762)

2024-03-02 00:50:01 -08:00

neuron_worker.py

[Neuron] Support inference with transformers-neuronx (#2569)

2024-02-28 09:34:34 -08:00

worker.py

[ROCm] enable cupy in order to enable cudagraph mode for AMD GPUs (#3123)

2024-03-04 18:14:53 -08:00