ljss e1054247ba [Optimization] Implement fused add rmsnorm (#1667)

2023-11-18 18:18:02 -08:00

..

quantization

Add AWQ support for all models (#1714)

2023-11-18 17:56:47 -08:00

__init__.py

Change the name to vLLM (#150)

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

activation.py

Add AWQ support for all models (#1714)

2023-11-18 17:56:47 -08:00

attention.py

[Minor] Move RoPE selection logic to get_rope (#1633)

2023-11-12 16:04:50 -08:00

layernorm.py

[Optimization] Implement fused add rmsnorm (#1667)

2023-11-18 18:18:02 -08:00

linear.py

TP/quantization/weight loading refactor part 2 - Refactor quantized linear logic and extend quantization support to all models (#1622)

2023-11-15 22:50:41 -08:00

rotary_embedding.py

[Minor] Move RoPE selection logic to get_rope (#1633)

2023-11-12 16:04:50 -08:00

sampler.py

Support Min P Sampler (#1642)

2023-11-17 16:20:49 -08:00

vocab_parallel_embedding.py

TP/quantization/weight loading refactor part 2 - Refactor quantized linear logic and extend quantization support to all models (#1622)

2023-11-15 22:50:41 -08:00