Enable accuracy test for eagle3 and chunked prefill

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                    | Untested        | No       | ---                       |                           |               |                  |                |                        |                       |                 |
-| EAGLE-3(Two Model Engine)  | NO                | Yes        | Yes                        | No                    | Untested        | No       | No                        | ---                       |               |                  |                |                        |                       |                 |
+| EAGLE-3(One Model Engine)  | Yes               | Yes        | Yes                        | No                    | Yes                   | No       | ---                       |                           |               |                  |                |                        |                       |                 |
+| EAGLE-3(Two Model Engine)  | NO                | Yes        | Yes                        | No                    | 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/accuracy/test_llm_api_pytorch.py

@@ -1817,7 +1817,9 @@ def test_bf16(self, tp_size, pp_size, ep_size, attention_dp, cuda_graph,
             task = MMLU(self.MODEL_NAME)
             task.evaluate(llm)
 
-    def test_eagle3(self):
+    @parametrize_with_ids("eagle3_one_model", [True, False])
+    @parametrize_with_ids("enable_chunked_prefill", [False, True])
+    def test_eagle3(self, enable_chunked_prefill, eagle3_one_model):
         pytorch_config = dict(
             disable_overlap_scheduler=True,
             cuda_graph_config=CudaGraphConfig(batch_sizes=[1]),
@@ -1829,11 +1831,13 @@ def test_eagle3(self):
 
         draft_len = 4
         spec_config = EagleDecodingConfig(max_draft_len=draft_len,
-                                          speculative_model_dir=eagle_model_dir)
+                                          speculative_model_dir=eagle_model_dir,
+                                          eagle3_one_model=eagle3_one_model)
 
         llm = LLM(model=target_model_dir,
                   **pytorch_config,
                   kv_cache_config=kv_cache_config,
+                  enable_chunked_prefill=enable_chunked_prefill,
                   speculative_config=spec_config,
                   build_config=None)
 

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

@@ -43,7 +43,10 @@ l0_h100:
   - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_fp8_block_scales[latency]
   - 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_8B::test_eagle3
+  - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3[enable_chunked_prefill=False-eagle3_one_model=False]
+  - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3[enable_chunked_prefill=True-eagle3_one_model=True]
+  - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3[enable_chunked_prefill=False-eagle3_one_model=True]
+  - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3[enable_chunked_prefill=True-eagle3_one_model=False]
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales_cuda_graph_padding[mtp_nextn=0]
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales_cuda_graph_padding[mtp_nextn=2]
   - test_e2e.py::test_trtllm_bench_pytorch_backend_sanity[meta-llama/Llama-3.1-8B-llama-3.1-8b-False-False]