[TRTLLM-12669][chore] remove allow_advanced_sampling from Nemotron docs/config

zhaoyangwang-nvidia · zhaoyangwang-nvidia · commit 5a9f69016274 · 2026-05-29T02:57:57.000-07:00
Signed-off-by: ZhaoyangWang &lt;zhaoyangw@nvidia.com&gt;
diff --git a/examples/models/core/nemotron/README_nemotron_super_v3.md b/examples/models/core/nemotron/README_nemotron_super_v3.md
@@ -144,7 +144,6 @@ kv_cache_config:
 speculative_config:
   decoding_type: MTP
   max_draft_len: 5
-  allow_advanced_sampling: true
 cuda_graph_config:
   max_batch_size: 64
   enable_padding: true
diff --git a/tests/integration/defs/examples/serve/test_configs/Nemotron3_Super_120B_NVFP4.yml b/tests/integration/defs/examples/serve/test_configs/Nemotron3_Super_120B_NVFP4.yml
@@ -23,4 +23,3 @@ print_iter_log: true
 speculative_config:
   decoding_type: MTP
   num_nextn_predict_layers: 3
-  allow_advanced_sampling: true
