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

..

layers

DeepseekMoE support with Fused MoE kernel (#2453)

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

models

DeepseekMoE support with Fused MoE kernel (#2453)

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

parallel_utils

Implement custom all reduce kernels (#2192)

2024-01-27 12:46:35 -08:00

__init__.py

Refactor Worker & InputMetadata (#1843)

2023-11-29 22:16:37 -08:00

input_metadata.py

Support FP8-E5M2 KV Cache (#2279)

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

model_loader.py

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

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

sampling_metadata.py

Use NCCL instead of ray for control-plane communication to remove serialization overhead (#2221)

2024-01-03 11:30:22 -08:00

utils.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

weight_utils.py

[Bugfix] fix load local safetensors model (#2512)

2024-01-19 16:26:16 -08:00