eigen 6ad6c8c9e6 feat: openai oss attention sink support with trtllm-gen backend #8825 (#8834) ...

Co-authored-by: averyhuang <averyh@nvidia.com>

2025-08-06 19:18:27 -07:00

..

cuda_graph_runner.py

Rename lora_path to lora_id in batches (#8437)

2025-08-03 21:08:28 -07:00

forward_batch_info.py

Use reduce scatter for DP (#8539)

2025-08-06 16:21:26 -07:00

model_runner.py

feat: openai oss attention sink support with trtllm-gen backend #8825 (#8834)

2025-08-06 19:18:27 -07:00