kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-20 01:35:27 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
1e317c98c6
TensorRT-LLMs/tensorrt_llm/_torch/models
History
Yukun He 9cc5922a0b
Clean up allreduce op in Deepseek V3 model. (#3829) 
* Replace deepseek_allreduce op with the new unified allreduce op and moe_allreduce op.
* Minor revision of moe_allreduce op argument names.

Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
2025-05-01 07:56:36 +08:00
..
__init__.py feat: Mistral-Large-2 support in the Pytorch workflow 2025-04-30 20:12:39 +08:00
.gitkeep Update TensorRT-LLM (#2755) 2025-02-11 03:01:00 +00:00
modeling_auto.py Fix create_weights in attention (#3692) 2025-04-24 07:30:00 +08:00
modeling_bert.py feat: Support cos_sin_cache in all cases. (#3517) 2025-04-16 13:48:44 +08:00
modeling_deepseekv3.py Clean up allreduce op in Deepseek V3 model. (#3829) 2025-05-01 07:56:36 +08:00
modeling_llama.py [fix] Fix flashinfer + speculation issues (#3686) 2025-04-28 14:34:22 -04:00
modeling_llava_next.py feat: llama4 input processor (#3383) 2025-04-25 16:47:14 -07:00
modeling_mamba_hybrid.py feat: Support cos_sin_cache in all cases. (#3517) 2025-04-16 13:48:44 +08:00
modeling_mistral.py feat: Mistral-Large-2 support in the Pytorch workflow 2025-04-30 20:12:39 +08:00
modeling_mixtral.py feat: Support cos_sin_cache in all cases. (#3517) 2025-04-16 13:48:44 +08:00
modeling_mllama.py chore: Use ellipsis as default value to detect whether residual argument is provided (#3626) 2025-04-17 12:31:58 +08:00
modeling_multimodal_encoder.py Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
modeling_multimodal_utils.py feat: llama4 input processor (#3383) 2025-04-25 16:47:14 -07:00
modeling_nemotron_h.py Support NemotronH FP8 Quantization 2025-04-29 18:51:43 +03:00
modeling_nemotron_nas.py Fix create_weights in attention (#3692) 2025-04-24 07:30:00 +08:00
modeling_nemotron.py feat: Support cos_sin_cache in all cases. (#3517) 2025-04-16 13:48:44 +08:00
modeling_qwen2vl.py feat: llama4 input processor (#3383) 2025-04-25 16:47:14 -07:00
modeling_qwen_moe.py feat: Support cos_sin_cache in all cases. (#3517) 2025-04-16 13:48:44 +08:00
modeling_qwen.py feat: Support cos_sin_cache in all cases. (#3517) 2025-04-16 13:48:44 +08:00
modeling_utils.py chore: bump version to 0.19.0 (#3598) (#3841) 2025-04-29 16:57:22 +08:00
modeling_vila.py feat: llama4 input processor (#3383) 2025-04-25 16:47:14 -07:00