Woosuk KwonandOne e67b4f2c2a Use FP32 in RoPE initialization (#1004) ...

Co-authored-by: One <imone@tuta.io>

2023-09-11 00:26:35 -07:00

..

__init__.py

Change the name to vLLM (#150)

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

activation.py

Implement approximate GELU kernels (#828)

2023-08-23 07:43:21 +09:00

attention.py

Use FP32 in RoPE initialization (#1004)

2023-09-11 00:26:35 -07:00

layernorm.py

Change the name to vLLM (#150)

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

sampler.py

Align vLLM's beam search implementation with HF generate (#857)

2023-09-04 17:29:42 -07:00