wangding zengandroy 5d60def02c DeepseekMoE support with Fused MoE kernel (#2453) ...

Co-authored-by: roy <jasonailu87@gmail.com>

2024-01-29 21:19:48 -08:00

..

quantization

AWQ: Up to 2.66x higher throughput (#2566)

2024-01-26 23:53:17 -08:00

triton_kernel

[Experimental] Prefix Caching Support (#1669)

2024-01-17 16:32:10 -08:00

__init__.py

Change the name to vLLM (#150)

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

activation.py

Add PyTorch-native implementation of custom layers (#1898)

2023-12-02 21:18:40 -08:00

attention.py

Support FP8-E5M2 KV Cache (#2279)

2024-01-28 16:43:54 -08:00

fused_moe.py

DeepseekMoE support with Fused MoE kernel (#2453)

2024-01-29 21:19:48 -08:00

layernorm.py

Add PyTorch-native implementation of custom layers (#1898)

2023-12-02 21:18:40 -08:00

linear.py

fix weigit loading for GQA with TP (#2379)

2024-01-15 15:43:59 -08:00

rejection_sampler.py

[Speculative decoding 1/9] Optimized rejection sampler (#2336)

2024-01-09 15:38:41 -08:00

rotary_embedding.py

Add PyTorch-native implementation of custom layers (#1898)

2023-12-02 21:18:40 -08:00

sampler.py

[Experimental] Add multi-LoRA support (#1804)

2024-01-23 15:26:37 -08:00

vocab_parallel_embedding.py

[Experimental] Add multi-LoRA support (#1804)

2024-01-23 15:26:37 -08:00