kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-13 22:18:36 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[https://nvbugs/5695984][fix] Unwaive llama3 eagle test (#10092)

Browse Source 
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
This commit is contained in:
Mike Iovine 2026-01-05 16:03:35 -05:00 committed by GitHub
parent 6b71b03947
commit 7a2dab8e85
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 1 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tests/integration/defs/accuracy/test_llm_api_pytorch.py
View File

@ -620,7 +620,7 @@ class TestLlama3_3_70BInstruct(LlmapiAccuracyTestHarness):
model_path = f"{llm_models_root()}/modelopt-hf-model-hub/Llama-3.3-70B-Instruct-fp8"
eagle_model_dir = f"{llm_models_root()}/EAGLE3-LLaMA3.3-Instruct-70B"
kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.6)
spec_config = EagleDecodingConfig(max_draft_len=4,
spec_config = EagleDecodingConfig(max_draft_len=3,
speculative_model_dir=eagle_model_dir,
eagle3_one_model=eagle3_one_model)
torch_compile_config = _get_default_torch_compile_config(torch_compile)

2
tests/integration/test_lists/waives.txt
View File

@ -486,8 +486,6 @@ accuracy/test_cli_flow.py::TestVicuna7B::test_eagle_2[cuda_graph=True-chunked_co
accuracy/test_cli_flow.py::TestVicuna7B::test_eagle_2[cuda_graph=True-chunked_context=False] SKIP (https://nvbugs/5773185)
accuracy/test_disaggregated_serving.py::TestGPTOSS::test_auto_dtype[True] SKIP (https://nvbugs/5596343)
accuracy/test_disaggregated_serving.py::TestGPTOSS::test_auto_dtype[False] SKIP (https://nvbugs/5596343)
accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_fp8_eagle3_tp8[eagle3_one_model=True-torch_compile=False] SKIP (https://nvbugs/5596343)
accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_fp8_eagle3_tp8[eagle3_one_model=False-torch_compile=False] SKIP (https://nvbugs/5596343)
accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_fp8_eagle3_tp8[eagle3_one_model=False-torch_compile=True] SKIP (https://nvbugs/5775326)
accuracy/test_llm_api_pytorch.py::TestQwen3_235B_A22B::test_fp8[throughput_latency] SKIP (https://nvbugs/5775544)
accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B_Instruct_2507::test_skip_softmax_attention[target_sparsity_0.5] SKIP (https://nvbugs/5774869)