Yang Fan a7c871680e Fix tie_word_embeddings for Qwen2. (#3344)

2024-03-15 09:36:53 -07:00

..

layers

fix marlin config repr (#3414)

2024-03-14 16:26:19 -07:00

models

Fix tie_word_embeddings for Qwen2. (#3344)

2024-03-15 09:36:53 -07:00

parallel_utils

Fix dist.broadcast stall without group argument (#3408)

2024-03-14 23:25:05 -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