[TRTLLM-13050][test] Remove two-model eagle3 spec-decoding tests (#14735)

Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>

Author: QiJune

tests/integration/test_lists/test-db/l0_dgx_b200.yml

@@ -295,14 +295,8 @@ l0_dgx_b200:
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v2_kv_cache-trtllm-one_model-overlap_scheduler]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v1_kv_cache-trtllm-one_model-no_overlap_scheduler]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v2_kv_cache-trtllm-one_model-no_overlap_scheduler]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v1_kv_cache-trtllm-two_model-no_overlap_scheduler]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v2_kv_cache-trtllm-two_model-no_overlap_scheduler]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v1_kv_cache-cutlass-one_model-no_overlap_scheduler]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v2_kv_cache-cutlass-one_model-no_overlap_scheduler]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v1_kv_cache-cutlass-two_model-overlap_scheduler]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v2_kv_cache-cutlass-two_model-overlap_scheduler]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v1_kv_cache-cutlass-two_model-no_overlap_scheduler]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v2_kv_cache-cutlass-two_model-no_overlap_scheduler]
   - unittest/_torch/multi_gpu_modeling -k "deepseek"
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8_4gpus[pp4-fp8kv=True-attn_backend=TRTLLM-torch_compile=False]
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTEDSL-mtp_nextn=2-ep4-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-low_precision_combine=False-torch_compile=False]

tests/integration/test_lists/test-db/l0_dgx_h100.yml

@@ -20,11 +20,9 @@ l0_dgx_h100:
   - unittest/_torch/multi_gpu -m "not post_merge" TIMEOUT (90)
   - unittest/_torch/modeling/test_modeling_pixtral.py::test_tensor_parallelism
   # ------------- Disaggregated serving tests ---------------
-  - accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_eagle3[eagle3_one_model=False-overlap_scheduler=False]
   - accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_eagle3[eagle3_one_model=True-overlap_scheduler=True]
   - accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_guided_decoding[xgrammar]
   - accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_guided_decoding_with_eagle3[xgrammar-eagle3_one_model=True]
-  - accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_guided_decoding_with_eagle3[xgrammar-eagle3_one_model=False]
   - accuracy/test_disaggregated_serving.py::TestQwen3_8B::test_auto_dtype[False-True]
   - accuracy/test_disaggregated_serving.py::TestQwen3_8B::test_auto_dtype[True-True]
   - accuracy/test_disaggregated_serving.py::TestQwen3_8B::test_auto_dtype[False-False]
@@ -74,9 +72,7 @@ l0_dgx_h100:
       orchestrator: mpi
   tests:
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_2gpus[cutlass-one_model-overlap_scheduler]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_2gpus[cutlass-two_model-overlap_scheduler]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_2gpus[triton-one_model-overlap_scheduler]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_2gpus[triton-two_model-overlap_scheduler]
 - condition:
     ranges:
       system_gpu_count:

tests/integration/test_lists/test-db/l0_gb200_multi_gpus.yml

@@ -76,8 +76,6 @@ l0_gb200_multi_gpus:
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-ep4-triton-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-dp4-trtllm-fp8]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4a16[dp4-fp8]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v1_kv_cache-trtllm-two_model-overlap_scheduler]
-  - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v2_kv_cache-trtllm-two_model-overlap_scheduler]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v1_kv_cache-cutlass-one_model-overlap_scheduler]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v2_kv_cache-cutlass-one_model-overlap_scheduler]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v1_kv_cache-trtllm-one_model-overlap_scheduler]

tests/integration/test_lists/test-db/l0_h100.yml

@@ -98,12 +98,10 @@ l0_h100:
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_dummy_load_format
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_guided_decoding[xgrammar]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_guided_decoding_with_eagle3[xgrammar-eagle3_one_model=True]
-  - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_guided_decoding_with_eagle3[xgrammar-eagle3_one_model=False]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8[fp8kv=False-attn_backend=TRTLLM-torch_compile=False]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8[fp8kv=False-attn_backend=TRTLLM-torch_compile=True]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8[fp8kv=True-attn_backend=TRTLLM-torch_compile=False]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8[fp8kv=True-attn_backend=TRTLLM-torch_compile=True]
-  - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_eagle3[sampler_async_worker=False-eagle3_one_model=False-overlap_scheduler=False]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_eagle3[sampler_async_worker=False-eagle3_one_model=True-overlap_scheduler=True]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_eagle3[sampler_async_worker=True-eagle3_one_model=True-overlap_scheduler=True]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_pard[overlap_scheduler=True]
@@ -127,10 +125,8 @@ l0_h100:
   - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_fp8[latency-torch_compile=False]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_fp8[latency-torch_compile=True]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_dummy_load_format
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3[eagle3_one_model=False-enable_chunked_prefill=False-enable_max_concurrency=False-enable_draft_len_schedule=False]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3[eagle3_one_model=True-enable_chunked_prefill=True-enable_max_concurrency=False-enable_draft_len_schedule=False]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3[eagle3_one_model=True-enable_chunked_prefill=False-enable_max_concurrency=False-enable_draft_len_schedule=False]
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3[eagle3_one_model=False-enable_chunked_prefill=True-enable_max_concurrency=False-enable_draft_len_schedule=False]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3[eagle3_one_model=True-enable_chunked_prefill=False-enable_max_concurrency=False-enable_draft_len_schedule=True]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3[eagle3_one_model=True-enable_chunked_prefill=False-enable_max_concurrency=True-enable_draft_len_schedule=False]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_dflash
@@ -360,7 +356,6 @@ l0_h100:
   - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_fp8_block_scales[latency-torch_compile=True]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_guided_decoding[llguidance]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_guided_decoding_with_eagle3[llguidance-eagle3_one_model=True]
-  - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_guided_decoding_with_eagle3[llguidance-eagle3_one_model=False]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_guided_decoding_with_ngram[xgrammar]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_guided_decoding_with_ngram[llguidance]
   - accuracy/test_llm_api_pytorch_multimodal.py::TestMistralSmall24B::test_auto_dtype[forced_chunked_prefill]