@@ -8,7 +8,7 @@ Add a one line overview of what this PR aims to accomplish.
 
 # GitHub Actions CI
 
-See the [CI section](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/CONTRIBUTING.md#-running-github-ci)in the Contributing doc for how to trigger the CI. A Nvidia developer will need to approve and trigger the CI for external contributors.
+See the [CI section](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/CONTRIBUTING.md#-running-github-ci) in the Contributing doc for how to trigger the CI. A Nvidia developer will need to approve and trigger the CI for external contributors.
 
 # Before your PR is "Ready for review"
 
 
@@ -1 +1 @@
-2d1fa8d372a3990b0bb1334cd686f15005ee138f
+b2a8ec7458e90216e3a8d147d8ddf81cfb895f7c
@@ -11,33 +11,33 @@
 </div>
 
 ## 📣 News
-- [05/06/2026] [**Gemma 4 VL 26B-A4B**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/vlm/gemma4_vl) is now supported! Checkpoint conversion, SFT, and PEFT (LoRA) recipes for Google's MoE vision-language model (26B total / 4B active params, 128 experts top-k=8, dual sliding/global attention with K=V tying on full-attention layers) are available on **main**. See the [examples README](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/vlm/gemma4_vl/README.md) for the full walkthrough.
+- [05/06/2026] [**Gemma 4 VL 26B-A4B**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/gemma/gemma4_vl) is now supported! Checkpoint conversion, SFT, and PEFT (LoRA) recipes for Google's MoE vision-language model (26B total / 4B active params, 128 experts top-k=8, dual sliding/global attention with K=V tying on full-attention layers) are available on **main**. See the [examples README](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/gemma/gemma4_vl/README.md) for the full walkthrough.
 
 - [04/28/2026] Day 0 support for [**Nemotron-3 Nano Omni**](https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16), a 30B-A3B MoE multimodal model that jointly processes image, video, audio, and text. Checkpoint conversion, SFT, and LoRA recipes are available on the [`nemotron_3_omni`](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/nemotron_3_omni) branch — see the [examples README](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/nemotron_3_omni/examples/models/vlm/nemotron_3_omni/README.md) for the full walkthrough.
 
 - [04/19/2026] [**Qwen3.6-35B-A3B**](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) is now supported! Qwen3.6 uses the same architecture as Qwen3.5 VL MoE (`Qwen3_5MoeForConditionalGeneration`) and works with the existing [Qwen3.5-VL bridge](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/src/megatron/bridge/models/qwen_vl) out of the box — no code changes needed. HF→Megatron conversion and inference verified.
 
 - [04/16/2026] **Megatron Bridge 0.4.0 released!** New model support (Kimi 2.5, Nemotron 3 Super, Qwen 3.5 VL, MiniMax M2, Sarvam, MiMo, and more), diffusion model collection, sequence-packing improvements, FP8 export, pruning & quantization, Transformers 5.x compatibility, and Python 3.12 migration. Huge thanks to our community contributors: [@HollowMan6](https://github.com/HollowMan6), [@shaltielshmid](https://github.com/shaltielshmid), [@jaeminh](https://github.com/jaeminh), [@pavelgein](https://github.com/pavelgein), [@ShiftyBlock](https://github.com/ShiftyBlock), [@erictang000](https://github.com/erictang000), [@eternally-z](https://github.com/eternally-z), [@Hayak3](https://github.com/Hayak3), and [@mohit-sarvam](https://github.com/mohit-sarvam)! See the [full release notes](https://github.com/NVIDIA-NeMo/Megatron-Bridge/releases/tag/v0.4.0).
 
-- [04/12/2026] [**MiniMax-M2.5 / M2.7**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/minimax_m2) are now supported! Both models share the same architecture as MiniMax-M2 and work with the existing bridge out of the box — checkpoint conversion and inference verified on real FP8 checkpoints.
+- [04/12/2026] [**MiniMax-M2.5 / M2.7**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/minimax/minimax_m2) are now supported! Both models share the same architecture as MiniMax-M2 and work with the existing bridge out of the box — checkpoint conversion and inference verified on real FP8 checkpoints.
 
-- [04/10/2026] [**Qwen3-ASR**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/audio_lm/qwen3_asr) is now supported! Checkpoint conversion and inference for [Qwen3's ASR model](https://github.com/QwenLM/Qwen3-ASR) are available on **main**.
+- [04/10/2026] [**Qwen3-ASR**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/qwen/qwen3_asr) is now supported! Checkpoint conversion and inference for [Qwen3's ASR model](https://github.com/QwenLM/Qwen3-ASR) are available on **main**.
 
 - [04/09/2026] [**Bailing MoE V2**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/bailing) is now supported! Checkpoint conversion and inference for the Bailing MoE V2 model are available on **main**. Thank you to [@ccclyu](https://github.com/ccclyu) for the community contribution!
 
 - [04/07/2026] Megatron Bridge’s PEFT support was featured at [PyTorch Conference Europe 2026 Talk](https://pytorchconferenceeu2026.sched.com/event/2Juce/optimizing-reinforcement-learning-at-trillion-parameter-scale-songlin-jiang-aalto-university-mind-lab).
 
-- [04/01/2026] [**Kimi K2.5 VL**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/vlm/kimi_k25_vl) is now supported! Checkpoint conversion, inference, and training recipes for [Moonshot AI’s Kimi-K2.5-VL](https://huggingface.co/moonshotai/Kimi-K2.5) vision-language model are available on **main**.
+- [04/01/2026] [**Kimi K2.5 VL**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/kimi/kimi_k25_vl) is now supported! Checkpoint conversion, inference, and training recipes for [Moonshot AI’s Kimi-K2.5-VL](https://huggingface.co/moonshotai/Kimi-K2.5) vision-language model are available on **main**.
 
 - [03/31/2026] **Agent Skills for Megatron Bridge!** We've added a [`skills/`](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/skills) directory with structured guides that AI coding agents (Cursor, Claude Code, Codex, etc.) can use to help you add model support, set up dev environments, tune performance, and more. Try them out, and PRs to improve or add new skills are very welcome!
 
-- [03/26/2026] [**Nemotron 3 Super**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/nemotron_3) is now on **main**! Checkpoint conversion and SFT/LoRA recipes (120B-A12B) are available in the main branch. Read the [blog post](https://developer.nvidia.com/blog/introducing-nemotron-3-super-an-open-hybrid-mamba-transformer-moe-for-agentic-reasoning/).
+- [03/26/2026] [**Nemotron 3 Super**](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/nemotron/nemotron_3) is now on **main**! Checkpoint conversion and SFT/LoRA recipes (120B-A12B) are available in the main branch. Read the [blog post](https://developer.nvidia.com/blog/introducing-nemotron-3-super-an-open-hybrid-mamba-transformer-moe-for-agentic-reasoning/).
 
 - [03/12/2026] **Deprecating Python 3.10 support:** We're officially dropping Python 3.10 support with the upcoming 0.4.0 release. Downstream applications must raise their lower boundary to 3.12 to stay compatible with Megatron-Bridge.
 
 - [12/16/2025] [Mind Lab](https://macaron.im/mindlab) successfully used Megatron-bridge and [VeRL](https://github.com/volcengine/verl) to trained GRPO Lora for Trillion-parameter model on 64 H800 - See their [techblog](https://macaron.im/mindlab/research/building-trillion-parameter-reasoning-rl-with-10-gpus).
 
-- [12/15/2025] Day 0 support for [NVIDIA-NeMotron-3-Nano-30B-A3B-FP8](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8)! [Reproducible code](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/nemotron_3/nano) and custom NGC container: [nvcr.io/nvidia/nemo:25.11.nemotron_3_nano](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo?version=25.11.nemotron_3_nano)
+- [12/15/2025] Day 0 support for [NVIDIA-NeMotron-3-Nano-30B-A3B-FP8](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8)! [Reproducible code](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/nemotron/nemotron_3/nano) and custom NGC container: [nvcr.io/nvidia/nemo:25.11.nemotron_3_nano](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo?version=25.11.nemotron_3_nano)
 
 ## Overview
 
 
@@ -84,7 +84,12 @@ RUN pip install nvidia-cudnn-frontend==1.17.0 \
     "xgrammar>=0.1.32" \
     "tornado==6.5.5" \
     "black==26.3.1" \
-    "onnx==1.21.0"
+    "onnx==1.21.0" \
+    "notebook>=7.5.6" \
+    "jupyterlab>=4.5.7" \
+    "mistune>=3.2.1" && \
+    # Address CVE from transitive dependency
+    pip uninstall -y opencv-python-headless
 
 # Remove PyTorch's bundled third-party onnx source tree (build artifact, not used at runtime).
 # The actual onnx Python package is managed above via pip/uv; this stale copy triggers CVE scanners.
 
@@ -55,7 +55,6 @@ override-dependencies = [
     "nemo-run @ /opt/Run",
     "transformer-engine; sys_platform == 'never'",     # Installed by MBridge
     # Pinning versions to solve conflicts
-    "av==15.1.0",                               # Version 16.0.0 released recently and fails to install
     "webdataset==0.2.86",                       # fix for SB multimodal
     "pandas==2.2.3",
     "ctc_segmentation==1.7.4",
@@ -113,4 +112,7 @@ override-dependencies = [
     "opencv-python; sys_platform == 'never'",            # Use the dependency from the base pytorch container
     "langchain~=1.0.0",
     "langchain-core~=1.2.22",                            # GHSA-qh6h-p6c9-ff54
+    "decord; sys_platform == 'never'",                   # Optional dependency. Resolves CVE
+    "av; sys_platform == 'never'",                       # Optional dependency. Resolves CVE
+    "opencv-python-headless; sys_platform == 'never'",   # Optional dependency. Resolves CVE
 ]
@@ -3,12 +3,18 @@
 ```
 
 ```{toctree}
-:caption: Guides
+:caption: Performance
 :hidden:
 
-parallelisms.md
 performance-summary.md
 performance-summary-archive.md
+```
+
+```{toctree}
+:caption: Guides
+:hidden:
+
+parallelisms.md
 performance-guide.md
 recipe-usage.md
 nemo2-migration-guide.md
 
@@ -19,7 +19,7 @@ Megatron Bridge supports the following LLM families:
 | **LLaMA Nemotron** | [llama-nemotron.md](llama-nemotron.md) | NVIDIA LLaMA Nemotron models |
 | **Mistral** | [mistral.md](mistral.md) | Mistral AI models |
 | **Moonlight** | [moonlight.md](moonlight.md) | Moonlight model family |
-| **Nemotron-3** | [nemotron3.md](nemotron3.md) | NVIDIA Nemotron-3 models |
+| **Nemotron-3 Nano** | [nemotron3-nano.md](nemotron3-nano.md) | NVIDIA Nemotron-3 Nano models |
 | **Nemotron-3 Super** | [nemotron3-super.md](nemotron3-super.md) | NVIDIA Nemotron-3 Super models |
 | **Nemotron-H** | [nemotronh.md](nemotronh.md) | NVIDIA Nemotron-H models |
 | **OLMoE** | [olmoe.md](olmoe.md) | OLMoE (Open Language Model - Mixture of Experts) |
 
@@ -0,0 +1,34 @@
+# DeepSeek V4
+
+[DeepSeek-V4](https://github.com/deepseek-ai/DeepSeek-V4) is the next-generation Mixture-of-Experts language model from DeepSeek-AI. It extends the V3 design with **Hyper-Connections (mHC)** for multi-stream residual mixing, **Compressed Sparse Attention (CSA)** with a learned token-importance indexer (DSA), **hash-routed MoE layers** for the first few decoder blocks, and a refined **Multi-Token Prediction (MTP)** head with separate `e_proj` / `h_proj` projections.
+
+DeepSeek V4 models are supported via the Bridge system with auto-detected configuration and weight mapping.
+
+## Model Architecture Features
+
+- **Hybrid Attention (DSv4HybridSelfAttention)**: Per-layer mix of dense MLA and Compressed Sparse Attention selected by `compress_ratios`
+- **Compressed Sparse Attention (CSA)** with **DSA Indexer**: Top-k token selection over windowed keys; `index_n_heads`, `index_head_dim`, `index_topk` control the indexer
+- **Hyper-Connections (mHC)**: 4-stream residual mixing per layer (`hc_mult = 4`) with sinkhorn-iterated attention; per-MTP-layer `hc_head_*` learns output contraction
+- **Hash-Routed MoE**: First few decoder layers use a deterministic vocab → expert mapping (`tid2eid`) instead of softmax routing
+- **Multi-Token Prediction (MTP)**: One MTP layer with separate `e_proj` and `h_proj` projections (post-MCore #4518)
+- **YaRN RoPE**: `rotary_scaling_factor=16`, `original_max_position_embeddings=65536`; `mscale=mscale_all_dim=1.0` for V4
+- **Sigmoid Gating with Expert Bias**: `noaux_tc` load balancing, `sqrtsoftplus` scoring, expert bias enabled
+- **`o_groups` Output Projection**: `o_lora_rank` low-rank output projection split into `o_groups` parallel groups
+
+## Examples, Parallelism, and Limitations
+
+For checkpoint conversion and inference scripts, recommended parallelism settings, and current known limitations, see the [DeepSeek V4 examples README](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/deepseek_v4).
+
+## Hugging Face Model Cards & References
+
+### Hugging Face Model Cards
+- DeepSeek-V4-Flash: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash
+- DeepSeek-V4-Flash-Base: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Base
+- DeepSeek-V4-Pro: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro
+- DeepSeek-V4-Pro-Base: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-Base
+
+### Additional Resources
+- GitHub Repository: https://github.com/deepseek-ai/DeepSeek-V4
+
+## Related Docs
+- DeepSeek V4 examples: [examples/models/deepseek_v4/README.md](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/deepseek_v4)
@@ -182,7 +182,7 @@ uv run python -m torch.distributed.run --nproc-per-node=8 run/run_recipe.py \
 - Gemma 3 1B: https://huggingface.co/google/gemma-3-1b-it
 
 ## Related Docs
-- Gemma3 Vision-Language Models: [Gemma 3 VL](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/vlm/gemma3_vl/README.md)
+- Gemma3 Vision-Language Models: [Gemma 3 VL](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/gemma/gemma3_vl/README.md)
 - Recipe usage: [Recipe usage](../../recipe-usage.md)
 - Customizing the training recipe configuration: [Configuration overview](../../training/config-container-overview.md)
 - Training entry points: [Entry points](../../training/entry-points.md)
Original file line number	Diff line number	Diff line change
`@@ -1 +1 @@`
`1`		`-2d1fa8d372a3990b0bb1334cd686f15005ee138f`
	`1`	`+b2a8ec7458e90216e3a8d147d8ddf81cfb895f7c`