Terry 7e9bd08f60 Add batched RoPE kernel (#3095)

2024-03-13 13:45:26 -07:00

..

layers

Add batched RoPE kernel (#3095)

2024-03-13 13:45:26 -07:00

models

Support Mistral Model Inference with transformers-neuronx (#3153)

2024-03-11 13:19:51 -07:00

parallel_utils

Re-enable the 80 char line width limit (#3305)

2024-03-10 19:49:14 -07:00

__init__.py

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

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

guided_decoding.py

Re-enable the 80 char line width limit (#3305)

2024-03-10 19:49:14 -07:00

guided_logits_processors.py

Re-enable the 80 char line width limit (#3305)

2024-03-10 19:49:14 -07:00

input_metadata.py

Support FP8-E5M2 KV Cache (#2279)

2024-01-28 16:43:54 -08:00

model_loader.py

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

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

neuron_model_loader.py

Re-enable the 80 char line width limit (#3305)

2024-03-10 19:49:14 -07:00

sampling_metadata.py

Re-enable the 80 char line width limit (#3305)

2024-03-10 19:49:14 -07:00

utils.py

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

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

weight_utils.py

Move model filelocks from /tmp/ to ~/.cache/vllm/locks/ dir (#3241)

2024-03-08 13:33:10 -08:00