vllm/vllm/model_executor/layers
2023-10-10 19:37:42 -07:00
..
quantized_linear TP/quantization/weight loading refactor part 1 - Simplify parallel linear logic (#1181) 2023-10-02 15:36:09 -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 [Mistral] Mistral-7B-v0.1 support (#1196) 2023-09-28 10:41:03 -07:00
layernorm.py Change the name to vLLM (#150) 2023-06-17 03:07:40 -07:00
rotary_embedding.py Support Longchat and RoPE scaling (#555) 2023-09-27 03:36:02 -07:00
sampler.py change the timing of sorting logits (#1309) 2023-10-10 19:37:42 -07:00