vllm/cacheflow/models
2023-03-01 21:13:08 -08:00
..
__init__.py Add input metadata 2023-02-22 19:01:20 +00:00
attention.py Use FlashAttention for multi_query_kv_attention (#4) 2023-03-01 21:13:08 -08:00
input_metadata.py Fix attention 2023-02-23 23:02:25 +00:00
model_utils.py Fix a bug in tying OPT embeddings (#1) 2023-02-24 16:29:36 -08:00
opt.py Fix a bug in tying OPT embeddings (#1) 2023-02-24 16:29:36 -08:00
sample.py Fix sampler 2023-02-23 20:30:12 +00:00