Skip to content

Commit e9f78c6

Browse files
authored
[https://nvbugs/5625962][chore] unwaive DS-v32-fp4 tests (#8853)
Signed-off-by: Fanrong Li <[email protected]>
1 parent 00c0e6c commit e9f78c6

File tree

2 files changed

+5
-2
lines changed

2 files changed

+5
-2
lines changed

tests/integration/defs/accuracy/references/mmlu.yaml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -198,6 +198,11 @@ deepseek-ai/DeepSeek-V3.2-Exp:
198198
- quant_algo: FP8_BLOCK_SCALES
199199
spec_dec_algo: MTP
200200
accuracy: 88.2
201+
- quant_algo: NVFP4
202+
accuracy: 87.81
203+
- quant_algo: NVFP4
204+
spec_dec_algo: MTP
205+
accuracy: 87.81
201206
Qwen3/Qwen3-8B:
202207
- quant_algo: W4A8_MXFP4_FP8
203208
accuracy: 72.70

tests/integration/test_lists/waives.txt

Lines changed: 0 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -394,5 +394,3 @@ accuracy/test_disaggregated_serving.py::TestQwen3_30B_A3B::test_mixed_ctx_gen_mo
394394
accuracy/test_disaggregated_serving.py::TestGPTOSS::test_auto_dtype[True] SKIP (https://nvbugs/5624367)
395395
accuracy/test_disaggregated_serving.py::TestGPTOSS::test_auto_dtype[False] SKIP (https://nvbugs/5624367)
396396
disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[llama-v3-8b-hf] SKIP (https://nvbugs/5587574)
397-
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus[baseline] SKIP (https://nvbugs/5625962)
398-
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus[baseline_mtp1] SKIP (https://nvbugs/5625962)

0 commit comments

Comments
 (0)