kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-13 22:18:36 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][fix] Update branch with the correct extra_attrs fix (#9857)

Browse Source 
Signed-off-by: Jonas Li <6110159+longlee0622@users.noreply.github.com>
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
Co-authored-by: Yukun He <23156053+hyukn@users.noreply.github.com>
This commit is contained in:
Jonas Li 2025-12-10 10:42:35 +08:00 committed by GitHub
parent 92997d608f
commit b05481107c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 2 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tensorrt_llm/_torch/models/modeling_auto.py
View File

@ -43,7 +43,7 @@ class AutoModelForCausalLM(Generic[TModel, TConfig]):
config._frozen = False
config.skip_create_weights_in_init = True
config._frozen = True
extra_attrs = {}
extra_attrs = config.extra_attrs
with model_extra_attrs(extra_attrs):
model = cls(config)
model.extra_attrs = extra_attrs

6
tensorrt_llm/_torch/modules/linear.py
View File

@ -2098,12 +2098,6 @@ class Linear(nn.Module):
'cutlass', 'cublaslt', 'cuda_core'
]
# add a environment variable to override the nvfp4_allowed_backends
if os.environ.get("TLLM_OVERRIDE_NVFP4_ALLOWED_BACKENDS"):
# check that all the backends in override_nvfp4_allowed_backends are in the self.nvfp4_allowed_backends
self.nvfp4_allowed_backends = os.environ.get(
"TLLM_OVERRIDE_NVFP4_ALLOWED_BACKENDS").split(",")
local_in_features = in_features
local_out_features = out_features

3
tests/integration/test_lists/waives.txt
View File

@ -444,5 +444,4 @@ disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backen
disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[DeepSeek-V3-Lite-fp8] SKIP (https://nvbugs/5722653)
disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[llama-3.1-8b-instruct-hf-fp8] SKIP (https://nvbugs/5722653)
disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[llama-v3-8b-hf] SKIP (https://nvbugs/5722653)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_2gpus[cutlass-two_model-overlap_scheduler] SKIP (https://nvbugs/5702826)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[cutlass-two_model-overlap_scheduler] SKIP (https://nvbugs/5702826)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3[cutlass-two_model-overlap_scheduler] SKIP (https://nvbugs/5702826)