[https://nvbugs/5596343] [test] Update accuracy baseline for GPT-OSS-20B (#8842)

Signed-off-by: Dongfeng Yu <[email protected]>
Signed-off-by: dongfengy <[email protected]>
Signed-off-by: Xiwen Yu <[email protected]>

Author: VALLIS-NERIA

tests/integration/defs/accuracy/references/gsm8k.yaml

@@ -200,7 +200,7 @@ GPT-OSS/BF16:
   - accuracy: 90.3
   - kv_cache_quant_algo: FP8
     accuracy: 90.3
-GPT-OSS/MXFP4:
+GPT-OSS/120B-MXFP4:
   - accuracy: 90.3
   - quant_algo: W4A8_MXFP4_MXFP8
     accuracy: 90.3
@@ -217,5 +217,17 @@ GPT-OSS/MXFP4:
   - quant_algo: W4A16_MXFP4
     kv_cache_quant_algo: FP8
     accuracy: 90.3
+GPT-OSS/20B-MXFP4:
+  - accuracy: 85.0
+  - quant_algo: W4A8_MXFP4_MXFP8
+    accuracy: 85.0
+  - quant_algo: W4A8_MXFP4_MXFP8
+    kv_cache_quant_algo: FP8
+    accuracy: 85.0
+  - quant_algo: W4A16_MXFP4
+    accuracy: 85.0
+  - quant_algo: W4A16_MXFP4
+    kv_cache_quant_algo: FP8
+    accuracy: 85.0
 LGAI-EXAONE/EXAONE-4.0-32B:
   - accuracy: 88.36

tests/integration/defs/accuracy/test_llm_api_pytorch.py

@@ -3248,7 +3248,7 @@ def test_w4_1gpu(self, kv_cache_dtype, moe_backend, cuda_graph,
                   moe_config=MoeConfig(backend=moe_backend))
 
         with llm:
-            model_name = "GPT-OSS/MXFP4"
+            model_name = "GPT-OSS/20B-MXFP4"
             task = GSM8K(model_name)
             task.evaluate(llm,
                           extra_evaluator_kwargs=self.extra_evaluator_kwargs)
@@ -3296,7 +3296,7 @@ def test_w4_4gpus(self, kv_cache_dtype, moe_backend, tp_size, pp_size,
                   moe_config=MoeConfig(backend=moe_backend))
 
         with llm:
-            model_name = "GPT-OSS/MXFP4"
+            model_name = "GPT-OSS/120B-MXFP4"
             task = GSM8K(model_name)
             task.evaluate(llm,
                           extra_evaluator_kwargs=self.extra_evaluator_kwargs)
@@ -3383,7 +3383,7 @@ def test_w4_2gpus(self, kv_cache_dtype, moe_backend, tp_size, pp_size,
                   moe_config=MoeConfig(backend=moe_backend))
 
         with llm:
-            model_name = "GPT-OSS/MXFP4"
+            model_name = "GPT-OSS/20B-MXFP4"
             task = GSM8K(model_name)
             mocker.patch.object(GSM8K, "MAX_OUTPUT_LEN", 8192)
             mocker.patch.dict(GSM8K.EVALUATE_KWARGS,
@@ -3410,7 +3410,7 @@ def test_w4_chunked_prefill(self, kv_cache_dtype, moe_backend, mocker):
         kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.6,
                                         dtype=kv_cache_dtype)
 
-        model_name = "GPT-OSS/MXFP4"
+        model_name = "GPT-OSS/120B-MXFP4"
         with LLM(self.MODEL_PATH,
                  tensor_parallel_size=4,
                  pipeline_parallel_size=1,

tests/integration/test_lists/waives.txt

@@ -340,7 +340,6 @@ triton_server/test_triton_llm.py::test_llmapi_backend[1-0-enableDecoupleMode-ten
 cpp/test_e2e.py::test_benchmarks[gpt-80] SKIP (https://nvbugs/5601670)
 disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_bf16_empty_batch[DeepSeek-V3-Lite-bf16] SKIP (https://nvbugs/5601682)
 disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[llama-v3-8b-hf] SKIP (https://nvbugs/5587574)
-accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-trtllm-fp8] SKIP (https://nvbugs/5608790)
 full:H20-3e/accuracy/test_llm_api_pytorch.py::TestNemotronUltra::test_auto_dtype[tp8ep4-cuda_graph=True] SKIP (slow I/O)
 full:H20-3e/accuracy/test_llm_api_pytorch.py::TestKimiK2::test_fp8_blockscale[latency] SKIP (slow I/O)
 full:H20-3e/test_e2e.py::test_ptp_quickstart_advanced_multi_gpus[DeepSeek-V3-671B-FP8-DeepSeek-V3-0324-8] SKIP (slow I/O)