kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-22 03:35:00 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
b168adba70
TensorRT-LLMs/tensorrt_llm/_torch
History
liji-nv b168adba70
feat: Add NVFP4 UB pattern optimization pass in torch compile (#3371) 
* feat: Add NVFP4 UB pattern optimization pass in torch compile

* Add an additional flag for UB fp4 pattern to avoid inverse the scale
* Add NVFP4 related UB patterns

Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>

* Update atol, some points fails for B200 umbriel.

Signed-off-by: liji-nv <59594262+liji-nv@users.noreply.github.com>

---------

Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
Signed-off-by: liji-nv <59594262+liji-nv@users.noreply.github.com>
2025-04-11 21:25:29 +08:00
..
attention_backend chore: Refine attention backend interface. (#3271) 2025-04-09 02:34:53 +08:00
auto_deploy feat: [TRTLLM-3510] DeepseekV3 support in AutoDeploy (#3281) 2025-04-08 21:47:57 +08:00
compilation feat: Add NVFP4 UB pattern optimization pass in torch compile (#3371) 2025-04-11 21:25:29 +08:00
custom_ops feat: Add NVFP4 UB pattern optimization pass in torch compile (#3371) 2025-04-11 21:25:29 +08:00
models fix: mllama e2e pytorch flow fix (#3397) 2025-04-11 17:33:15 +08:00
modules feat: support llama4 nope layers; support FP8 checkpoint loading; (#3382) 2025-04-10 10:16:42 -07:00
peft lora_tests (#3201) 2025-04-09 18:06:52 +03:00
pyexecutor feat: Add NVFP4 UB pattern optimization pass in torch compile (#3371) 2025-04-11 21:25:29 +08:00
speculative fix the py_decoding_iter update in decoder. (#3297) 2025-04-07 11:18:33 +08:00
__init__.py Update TensorRT-LLM (#2755) 2025-02-11 03:01:00 +00:00
autotuner.py feat: Apply the new torch-flow compatible AutoTuner to both Fused MoE and NVFP4 Linear operators. (#3151) 2025-04-08 14:28:36 +08:00
distributed.py Update (#2978) 2025-03-23 16:39:35 +08:00
llm.py test: [TRTLLM-4334] Create 1.0 criteria scope from API stability references (#3069) 2025-03-26 18:14:35 +08:00
metadata.py feat: no-cache attention in PyTorch workflow (#3085) 2025-04-05 01:54:32 +08:00
model_config.py Add Llama 4 (#3302) 2025-04-09 03:35:21 +08:00
pipeline_interface.py Update (#2978) 2025-03-23 16:39:35 +08:00
utils.py feat: Add NVFP4 UB pattern optimization pass in torch compile (#3371) 2025-04-11 21:25:29 +08:00