kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
ff82aef99b
TensorRT-LLMs/tensorrt_llm/_torch/pyexecutor
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
..
__init__.py Update TensorRT-LLM (#2755) 2025-02-11 03:01:00 +00:00
_util.py feat: Run PyExecutor's inference flow to estimate max_num_tokens for kv_cache_manager (#3092) 2025-04-10 18:29:40 +08:00
config.py feat: Optionally split MoE inputs into chunks to reduce GPU memory usage (#3104) 2025-04-01 16:07:02 +08:00
cuda_graph_runner.py feat: Run PyExecutor's inference flow to estimate max_num_tokens for kv_cache_manager (#3092) 2025-04-10 18:29:40 +08:00
decoder.py fix the py_decoding_iter update in decoder. (#3297) 2025-04-07 11:18:33 +08:00
distributed.py Only gather responses on rank 0 (#3040) 2025-03-24 21:54:51 -07:00
guided_decoder.py Update (#2978) 2025-03-23 16:39:35 +08:00
kv_cache_transceiver.py Update TensorRT-LLM (#2849) 2025-03-04 18:44:00 +08:00
layerwise_nvtx_marker.py Update TensorRT-LLM (#2849) 2025-03-04 18:44:00 +08:00
llm_request.py feat: Run PyExecutor's inference flow to estimate max_num_tokens for kv_cache_manager (#3092) 2025-04-10 18:29:40 +08:00
model_engine.py feat: Add NVFP4 UB pattern optimization pass in torch compile (#3371) 2025-04-11 21:25:29 +08:00
py_executor_creator.py feat: Run PyExecutor's inference flow to estimate max_num_tokens for kv_cache_manager (#3092) 2025-04-10 18:29:40 +08:00
py_executor.py feat: Run PyExecutor's inference flow to estimate max_num_tokens for kv_cache_manager (#3092) 2025-04-10 18:29:40 +08:00
resource_manager.py feat: Support PeftCacheManager in Torch (#3186) 2025-04-04 12:38:08 +08:00
scheduler.py Update TensorRT-LLM (#2936) 2025-03-18 21:25:19 +08:00