@@ -34,16 +34,16 @@ l0_h100:
3434 - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8[fp8kv=False-attn_backend=TRTLLM-torch_compile=True]
3535 - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8[fp8kv=True-attn_backend=TRTLLM-torch_compile=False]
3636 - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8[fp8kv=True-attn_backend=TRTLLM-torch_compile=True]
37- - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_eagle3[overlap_scheduler =False-eagle3_one_model =False]
38- - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_eagle3[overlap_scheduler=False- eagle3_one_model=True]
37+ - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_eagle3[eagle3_one_model =False-overlap_scheduler =False]
38+ - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_eagle3[eagle3_one_model=True-overlap_scheduler=False ]
3939 - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales[mtp=disable-fp8kv=True-attention_dp=False-cuda_graph=True-overlap_scheduler=True-torch_compile=True]
4040 - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales[mtp=eagle-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False]
4141 - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales[mtp=vanilla-fp8kv=True-attention_dp=False-cuda_graph=True-overlap_scheduler=True-torch_compile=True]
4242 - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_no_kv_cache_reuse[quant_dtype=fp8-mtp_nextn=2-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True]
4343 - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_fp8_block_scales[latency]
4444 - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_fp8[latency]
45- - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3[overlap_scheduler =False-eagle3_one_model =False]
46- - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3[overlap_scheduler=False- eagle3_one_model=True]
45+ - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3[eagle3_one_model =False-overlap_scheduler =False]
46+ - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3[eagle3_one_model=True-overlap_scheduler=False ]
4747 - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales_cuda_graph_padding[mtp_nextn=0]
4848 - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales_cuda_graph_padding[mtp_nextn=2]
4949 - test_e2e.py::test_trtllm_bench_pytorch_backend_sanity[meta-llama/Llama-3.1-8B-llama-3.1-8b-False-False]
0 commit comments