We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent a49cfb3 commit a91453dCopy full SHA for a91453d
tests/unittest/llmapi/test_llm_pytorch.py
@@ -504,6 +504,7 @@ def test_nemotron_nas_lora() -> None:
504
505
506
@skip_gpu_memory_less_than_80gb
507
+@pytest.mark.skip(reason="https://nvbugs/5521949")
508
def test_codellama_fp8_with_bf16_lora() -> None:
509
model_dir = f"{llm_models_root()}/codellama/CodeLlama-7b-Instruct-hf/"
510
quant_config = QuantConfig(quant_algo=QuantAlgo.FP8,
@@ -564,6 +565,7 @@ def test_codellama_fp8_with_bf16_lora() -> None:
564
565
566
567
568
569
def test_bielik_11b_v2_2_instruct_multi_lora() -> None:
570
model_dir = f"{llm_models_root()}/Bielik-11B-v2.2-Instruct"
571
0 commit comments