[TRTLLM-17033][test] Run most qwen4_exp accuracy gates post-merge

Every gate builds the full Qwen3.8-Flash-Next-NVFP4 engine (a gsm8k gate is roughly 8-13 min on
one GB300), so the 26 pre-merge gates cost several GPU hours per CI run.

Pre-merge keeps main's three gates (gsm8k; gsm8k with one MTP draft and the acceptance-length
floor; mmmu with MTP) and adds the one gate that runs the sparse attention path: 3k-6k-token pass
keys with three drafts and IndexShare over bf16 KV.

Post-merge runs one gate per opt-in variant: MTP3 alone and over CuteDSL experts, MTP7 over long
pass keys, FP8 and NVFP4 KV over the pass keys, the bf16 recurrent state at MTP3, MTP7 all
rejected by forced acceptance, video, and the breakable prefill graph against eager.

The other gates stay in test_qwen4_exp.py for on-demand runs.

Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>

Author: Wanli-Jiang

tests/integration/test_lists/test-db/l0_b300.yml

@@ -136,46 +136,15 @@ l0_b300:
   # stage instead), so 30 is 2.5x headroom.
   - unittest/_torch/modeling_v2 --ignore=unittest/_torch/modeling_v2/comm TIMEOUT (30)
   - accuracy/modeling_v2/test_gpt_oss.py::TestModelingV2GptOss120bSm103Tp1::test_gsm8k
-  # qwen4_exp target: gsm8k, and gsm8k with the trunk's routed experts on CuteDSL;
-  # gsm8k with MTP plus the acceptance-length floor, the only gate that sees a
-  # miscomputed draft layer, at one draft over bf16 and fp8 KV, at three drafts
-  # alone and over CuteDSL experts, and at five and seven drafts (the verify step's
-  # six and eight rows per request); 3k-6k-token pass key prompts, the only cases that
-  # run the sparse attention path (IndexShare over bf16 KV, fp8 KV), and 3k-12k-token ones
-  # at seven drafts; seven drafts all rejected and all accepted by forced acceptance at
-  # batch 32 over long prompts; the recurrent-state verify path that
-  # TRTLLM_USE_GDN_REPLAY=0 selects; the recurrent state stored in bf16 without speculation,
-  # at three drafts and at seven drafts over long prompts; mmmu with MTP and synthetic
-  # videos, the only gates that reach the vision tower; and the opt-in breakable prefill
-  # CUDA graph: gsm8k, gsm8k with three drafts and the length floor, 3k-6k-token pass keys
-  # prefilled in replayed 2048-token chunks, mmmu, and replayed against eager greedy
-  # continuations at the bucket edges and with context and generation rows in one batch.
+  # qwen4_exp target, pre-merge: gsm8k; gsm8k with one MTP draft plus the
+  # acceptance-length floor, the only gate that sees a miscomputed draft layer;
+  # mmmu with MTP, which reaches the vision tower; and 3k-6k-token pass key prompts
+  # with three drafts and IndexShare over bf16 KV, the only prompts long enough to run
+  # the sparse attention path. The opt-in variants run post-merge (below).
   - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_gsm8k
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_gsm8k_cutedsl_moe
   - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp1_gsm8k_and_acceptance
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp1_fp8_kv_gsm8k_and_acceptance
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp1_nvfp4_kv_gsm8k_and_acceptance
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp3_gsm8k_and_acceptance
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp3_cutedsl_gsm8k_and_acceptance
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp5_gsm8k_and_acceptance
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp7_gsm8k_and_acceptance
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp3_long_context_passkey[index_share]
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp3_long_context_passkey[fp8_kv]
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp3_long_context_passkey[nvfp4_kv]
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp7_long_context_passkey
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp7_forced_acceptance_extremes[all_rejected]
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp7_forced_acceptance_extremes[all_accepted]
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_gsm8k_bf16_ssm_state
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp3_bf16_ssm_state_gsm8k_and_acceptance
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp7_bf16_ssm_state_long_context_passkey
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp1_gdn_legacy_verify
   - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp1_mmmu
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp1_video
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_gsm8k_breakable_prefill_cuda_graph
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp3_breakable_prefill_gsm8k_and_acceptance
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp3_long_context_passkey[breakable_prefill]
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp1_mmmu_breakable_prefill
-  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_breakable_prefill_matches_eager
+  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp3_long_context_passkey[index_share]
 - condition:
     ranges:
       system_gpu_count:
@@ -196,3 +165,20 @@ l0_b300:
   - unittest/_torch/moe/test_moe_backend.py::test_moe_backend -k "TRTLLM"
   - unittest/_torch/moe/test_moe_backend.py::test_moe_backend -k "CUTEDSL"
   - unittest/_torch/moe/test_moe_backend.py::test_moe_backend -k "DEEPGEMM"
+  # qwen4_exp target, post-merge: one gate per opt-in variant -- three drafts, alone and
+  # over CuteDSL experts; seven drafts over 3k-12k-token pass keys (the verify step's
+  # eight rows per request); fp8 and NVFP4 KV over the pass keys (their sparse attention
+  # path); the recurrent state in bf16 at three drafts; seven drafts all rejected by
+  # forced acceptance (the speculative rollback end to end); synthetic videos; and the
+  # breakable prefill CUDA graph replayed against eager greedy continuations at the bucket
+  # edges and with context and generation rows in one batch. The other gates in
+  # test_qwen4_exp.py run on demand.
+  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp3_gsm8k_and_acceptance
+  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp3_cutedsl_gsm8k_and_acceptance
+  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp7_long_context_passkey
+  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp3_long_context_passkey[fp8_kv]
+  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp3_long_context_passkey[nvfp4_kv]
+  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp3_bf16_ssm_state_gsm8k_and_acceptance
+  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp7_forced_acceptance_extremes[all_rejected]
+  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_mtp1_video
+  - accuracy/modeling_v2/test_qwen4_exp.py::TestModelingV2Qwen38FlashNextNvfp4Sm103Tp1::test_breakable_prefill_matches_eager