Popular repositories Loading

1. metaseq metaseq Public

   Forked from facebookresearch/metaseq

   Repo for external large-scale work

   Python

2. FasterTransformer FasterTransformer Public

   Forked from NVIDIA/FasterTransformer

   Transformer related optimization, including BERT, GPT

   C++

3. vllm-omni vllm-omni Public

   Forked from vllm-project/vllm-omni

   A framework for efficient model inference with omni-modality models

   Python

4. fast-ulysses fast-ulysses Public

   Forked from triple-mu/fast-ulysses

   Ulysses sequence-parallel all-to-all as a torch custom op, moved by the GPU copy engines into torch symmetric memory. Zero SM usage; 1.66-2.17x over torch.distributed on NVLink.

   Python