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

chore: skip test_llm_gpt2_medium_fp8 for fp8_pc_pt + quant_lm_head (#5293)

Browse Source 
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
This commit is contained in:
Aurelien Chartier 2025-06-18 11:13:12 -07:00 committed by GitHub
parent 5010f8719d
commit d25f93c07f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tests/integration/defs/examples/test_gpt.py
View File

@ -775,6 +775,8 @@ def test_llm_gpt2_int8_kv_1gpu(gpt_example_root, llm_venv, llm_gpt2_model_root,
def test_llm_gpt2_medium_fp8(gpt_example_root, llm_gpt2_medium_model_root,
llm_datasets_root, llm_rouge_root, llm_venv,
cmodel_dir, engine_dir, quant_lm_head, qformat):
if qformat == "fp8_pc_pt" and quant_lm_head:
pytest.skip("Skipping test for fp8_pc_pt with quant_lm_head")
"Build & Run gpt2-medium fp8 with 1 gpu"
print("Quantizing and converting checkpoint...")
dtype = "float16"