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

squash (#3642)

Browse Source 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
This commit is contained in:
Enwei Zhu 2025-04-17 10:41:56 +08:00 committed by GitHub
parent 715428cca9
commit e36092bd40
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tests/integration/test_lists/waives.txt
View File

@ -453,3 +453,4 @@ examples/test_medusa.py::test_codellama_medusa_1gpu[CodeLlama-7b-Instruct] SKIP
examples/test_medusa.py::test_llama_medusa_1gpu[llama-v2-7b-hf] SKIP (https://nvbugs/5219534)
examples/test_medusa.py::test_llama_medusa_1gpu[llama-3.2-1b] SKIP (https://nvbugs/5219534)
examples/test_medusa.py::test_llama_medusa_1gpu[llama-3.1-8b] SKIP (https://nvbugs/5219535)
examples/test_phi.py::test_llm_phi_quantization_1gpu[Phi-4-mini-instruct-fp8-bfloat16] SKIP (https://nvbugspro.nvidia.com/bug/5226339)

1
tests/unittest/_torch/thop/test_scaled_mm.py
View File

@ -38,6 +38,7 @@ from utils.util import getSMVersion
[torch.float16, torch.float32, torch.bfloat16],
)
def test_fp8_scaled_mm(output_dtype, m, k_n):
pytest.skip("https://nvbugspro.nvidia.com/bug/5228279")
# Skip specific problematic case
if m == 228 and k_n == (28672, 8192):
pytest.skip("Skipping problematic case with m=228, k=28672, n=8192")

1
tests/unittest/llmapi/test_llm_multi_gpu.py
View File

@ -312,6 +312,7 @@ def test_llm_multi_node_pytorch():
run_command(command)
@pytest.mark.skip(reason="https://nvbugspro.nvidia.com/bug/5223608: timeout")
@skip_single_gpu
def test_llm_multi_node_with_postproc():
# TODO[chunweiy]: reactivate this later