[None][infra] update feature_combination_matrix of disaggregated and Eagle3

Signed-off-by: leslie-fang25 <[email protected]>

Author: leslie-fang25

docs/source/torch/features/feature_combination_matrix.md

@@ -8,8 +8,8 @@
 | Disaggregated Serving      | Yes               | Yes        | Yes                        | ---                   |                 |          |                           |                           |               |                  |                |                        |                       |                 |
 | Chunked Prefill            | Yes               | Yes        | Yes                        | Untested              | ---             |          |                           |                           |               |                  |                |                        |                       |                 |
 | MTP                        | Yes               | Yes        | Yes                        | Yes                   | Untested        | ---      |                           |                           |               |                  |                |                        |                       |                 |
-| EAGLE-3(One Model Engine)  | Yes               | Yes        | Yes                        | No                    | Yes             | No       | ---                       |                           |               |                  |                |                        |                       |                 |
-| EAGLE-3(Two Model Engine)  | NO                | Yes        | Yes                        | No                    | Yes             | No       | No                        | ---                       |               |                  |                |                        |                       |                 |
+| EAGLE-3(One Model Engine)  | Yes               | Yes        | Yes                        | Yes                   | Yes             | No       | ---                       |                           |               |                  |                |                        |                       |                 |
+| EAGLE-3(Two Model Engine)  | NO                | Yes        | Yes                        | Yes                   | Yes             | No       | No                        | ---                       |               |                  |                |                        |                       |                 |
 | Torch Sampler              | Yes               | Yes        | Yes                        | Yes                   | Yes             | Yes      | Yes                       | Yes                       | ---           |                  |                |                        |                       |                 |
 | TLLM C++ Sampler           | Yes               | Yes        | Yes                        | Yes                   | Yes             | No       | No                        | No                        | No            | ---              |                |                        |                       |                 |
 | KV Cache Reuse             | Yes               | Yes        | Yes                        | Untested              | Yes             | Untested | Yes                       | No                        | Yes           | Yes              | ---            |                        |                       |                 |

tests/integration/defs/disaggregated/test_disaggregated_single_gpu.py

@@ -349,13 +349,15 @@ def test_disaggregated_llama_context_capacity(model, enable_cuda_graph,
 @pytest.mark.parametrize("model", ["Llama-3.1-8B-Instruct"])
 @pytest.mark.parametrize("spec_dec_model_path", ["EAGLE3-LLaMA3.1-Instruct-8B"])
 @pytest.mark.parametrize("generation_overlap", [False])
+@pytest.mark.parametrize("eagle3_one_model", [True, False])
 def test_disaggregated_spec_dec_batch_slot_limit(model, spec_dec_model_path,
-                                                 generation_overlap):
+                                                 generation_overlap,
+                                                 eagle3_one_model):
     # Test whether the batch slots are properly released when using speculative decoding
     # with disaggregated serving.
     spec_dec_config = EagleDecodingConfig(
         speculative_model_dir=model_path(spec_dec_model_path),
-        eagle3_one_model=False,
+        eagle3_one_model=eagle3_one_model,
         max_draft_len=3)
 
     worker_pytorch_configs = []

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

@@ -85,7 +85,8 @@ l0_h100:
   - disaggregated/test_workers.py::test_workers_kv_cache_aware_router[TinyLlama-1.1B-Chat-v1.0]
   - disaggregated/test_workers.py::test_workers_kv_cache_aware_router_eviction[TinyLlama-1.1B-Chat-v1.0]
   - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_llama_context_capacity[False-False-DeepSeek-V3-Lite-fp8/fp8]
-  - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_spec_dec_batch_slot_limit[False-EAGLE3-LLaMA3.1-Instruct-8B-Llama-3.1-8B-Instruct]
+  - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_spec_dec_batch_slot_limit[True-False-EAGLE3-LLaMA3.1-Instruct-8B-Llama-3.1-8B-Instruct]
+  - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_spec_dec_batch_slot_limit[False-False-EAGLE3-LLaMA3.1-Instruct-8B-Llama-3.1-8B-Instruct]
   - test_e2e.py::test_trtllm_bench_iteration_log[PyTorch-streaming-meta-llama/Llama-3.1-8B-llama-3.1-model/Meta-Llama-3.1-8B]
   - test_e2e.py::test_trtllm_bench_iteration_log[PyTorch-non-streaming-meta-llama/Llama-3.1-8B-llama-3.1-model/Meta-Llama-3.1-8B]
   - test_e2e.py::test_trtllm_bench_request_rate_and_concurrency[enable_concurrency-]