Skip to content

[https://nvbugs/5575913][fix] Use separate thresholds for 120b/20b gptoss #8664

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Oct 28, 2025
+18 −7
Merged

[https://nvbugs/5575913][fix] Use separate thresholds for 120b/20b gptoss #8664

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
36abc2c
[https://nvbugs/5575913][fix] Use separate thresholds for 2120b/20b g…
dongfengy Oct 25, 2025
195abda
Update waives.txt
dongfengy Oct 27, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 13 additions & 1 deletion tests/integration/defs/accuracy/references/gsm8k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -212,7 +212,7 @@ 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
Expand All @@ -229,6 +229,18 @@ 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
ByteDance-Seed/Seed-OSS-36B-Instruct:
Expand Down
10 changes: 5 additions & 5 deletions tests/integration/defs/accuracy/test_llm_api_pytorch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3450,7 +3450,7 @@ 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)
Expand All @@ -3461,7 +3461,7 @@ def test_dummy_load_format(self):
load_format="dummy",
)
with llm:
model_name = "GPT-OSS/MXFP4"
model_name = "GPT-OSS/20B-MXFP4"
task = GSM8K(model_name)
task.evaluate(llm, is_integration_test=True)

Expand Down Expand Up @@ -3509,7 +3509,7 @@ 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)
Expand Down Expand Up @@ -3636,7 +3636,7 @@ 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,
Expand All @@ -3663,7 +3663,7 @@ 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,
Expand Down
1 change: 0 additions & 1 deletion tests/integration/test_lists/waives.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -388,7 +388,6 @@ accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_ctx_pp_gen
accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_ctx_pp_gen_tp_asymmetric[GSM8K-gen_tp=2-ctx_pp=4] SKIP (https://nvbugs/5582277)
accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_ctx_pp_gen_tp_asymmetric[MMLU-gen_tp=2-ctx_pp=2] SKIP (https://nvbugs/5582277)
accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_ctx_pp_gen_tp_asymmetric[MMLU-gen_tp=2-ctx_pp=4] SKIP (https://nvbugs/5582277)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-trtllm-fp8] SKIP (https://nvbugs/5608790)
accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_bf16[multi_gpus_no_cache] SKIP (https://nvbugs/5547414)
triton_server/test_triton.py::test_llava[llava] SKIP (https://nvbugs/5547414)
disaggregated/test_workers.py::test_workers_kv_cache_aware_router[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/5607238)
Expand Down