Updated Nemotron to support dual sparks

README.md

@@ -149,6 +149,16 @@ Don't do it every time you rebuild, because it will slow down compilation times.
 
 For periodic maintenance, I recommend using a filter: `docker builder prune --filter until=72h`
 
+### 2026-03-12
+
+#### Nemotron-3-Super-120B NVFP4 Recipe
+
+Added a new recipe `nemotron-3-super-nvfp4` for running `nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4` with Marlin kernels. Supports both solo and cluster modes. Includes a custom reasoning parser (`super_v3_reasoning_parser.py`) fetched from the model repository. Supports both dual and single Spark configurations.
+
+```bash
+./run-recipe.sh nemotron-3-super-nvfp4
+```
+
 ### 2026-03-11
 
 #### Qwen3-Coder-Next INT4-AutoRound Recipe

recipes/nemotron-3-super-nvfp4.yaml

@@ -7,8 +7,7 @@ description: vLLM serving Nemotron-3-Super-120B using Marlin kernels
 model: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4
 container: vllm-node
 cluster_only: false
-# This model can only run on single node (solo)
+solo_only: false
-solo_only: true
 
 mods: 
   - mods/nemotron-super
@@ -17,7 +16,7 @@ container: vllm-node
 defaults:
   port: 8000
   host: 0.0.0.0
-  tensor_parallel: 1
+  tensor_parallel: 2
   gpu_memory_utilization: 0.7
   max_model_len: 262144
   max_num_seqs: 10
@@ -41,4 +40,6 @@ command: |
   --load-format fastsafetensors \
   --tool-call-parser qwen3_coder \
   --reasoning-parser-plugin super_v3_reasoning_parser.py \
-  --reasoning-parser super_v3
+  --reasoning-parser super_v3 \
+  --tensor-parallel-size {tensor_parallel} \
+  --distributed-executor-backend ray