theely · Jul 28, 2026 · Jul 28, 2026 · Jul 29, 2026 · Jul 30, 2026 · Jul 30, 2026
diff --git a/.dev.commit b/.dev.commit
@@ -1 +1 @@
-0e6ac576fba8995fca541ceb6af5f35eb0e4f16e
+43e45e13074f36da68b34c7a189cd997a01d1b41
diff --git a/README.md b/README.md
@@ -229,7 +229,7 @@ Megatron Bridge provides out-of-the-box bridges and training recipes for a wide
 | **Ernie** | [Ernie 4.5 MoE](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/src/megatron/bridge/models/ernie), [Ernie 4.5 VL MoE](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/src/megatron/bridge/models/ernie_vl) |
 | [**Falcon**](docs/models/falcon/index.md) | Falcon H1 |
 | [**Gemma**](docs/models/gemma/index.md) | Gemma / Gemma 2 (deprecated), Gemma 3, Gemma 3-VL, Gemma 4 (26B-A4B MoE / 31B dense), Gemma 4-VL (26B-A4B MoE) |
-| [**GLM**](docs/models/glm/index.md) | GLM-4.5 / 4.7 / 4.7-Flash, GLM-4.5V, GLM-5 / 5.1 |
+| [**GLM**](docs/models/glm/index.md) | GLM-4.5 / GLM-4.7 / GLM-4.7-Flash, GLM-4.5V, GLM-5 / GLM-5.1 / GLM-5.2 |
 | [**GPT-OSS**](docs/models/gpt_oss/index.md) | GPT-oss |
 | [**HY V3**](https://huggingface.co/tencent/Hy3-preview-Base) | Hy3 preview-Base (HF → Megatron checkpoint conversion) |
 | [**Kimi**](docs/models/kimi/index.md) | Kimi K2, Kimi-K2.5-VL |

@@ -65,8 +65,7 @@ ENV PATH="/opt/venv/bin:/opt/venv/bin:/root/.local/bin:$PATH" \
 RUN --mount=type=bind,source=docker/patches/deepep.patch,target=/opt/deepep.patch \
     curl -LsSf https://astral.sh/uv/${UV_VERSION}/install.sh | sh && \
     uv venv ${UV_PROJECT_ENVIRONMENT} --system-site-packages && \
-    # Address CVE-2025-68973
-    apt-get update && apt install -y --only-upgrade gnupg && \
+    apt-get update && apt install -y --only-upgrade gnupg openssl libssl3t64 && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/* && \
     if [ "$INSTALL_DEEPEP" = "True" ]; then \

@@ -71,35 +71,38 @@ RUN \
 ##
 ##############################################################################
 
-RUN pip install "starlette==0.49.1" \
+RUN pip install "fastapi==0.139.1" \
+    "starlette==1.3.1" \
+    "prometheus-fastapi-instrumentator>=8.0.0" \
     "urllib3>=2.7.0" \
     "aiohttp>=3.13.3" \
     "jaraco-context>=6.1.0" \
     "wheel>=0.46.2" \
     "python-multipart>=0.0.22" \
     "setuptools>=80.10.2" \
-    "pillow>=12.1.1" \
+    "pillow>=12.3.0" \
     "protobuf==6.33.5" \
     "xgrammar>=0.1.32" \
-    "tornado==6.5.5" \
+    "tornado==6.5.6" \
     "black==26.3.1" \
     "onnx==1.21.0" \
     "notebook>=7.5.6" \
-    "jupyterlab>=4.5.7" \
-    "jupyter-server>=2.18.0" \
-    "mistune>=3.2.1" \
-    "GitPython>=3.1.50" && \
+    "jupyterlab>=4.5.10" \
+    "jupyter-server>=2.20.0" \
+    "mistune>=3.3.0" \
+    "GitPython>=3.1.58" && \
     # Address CVE from transitive dependency
-    pip uninstall -y opencv-python-headless nvidia-dali-cuda130
-
+    # Remove the package pulled in by Humming kernels.
+    # Humming-backed vLLM quantization is unavailable without pyelftools.
+    pip uninstall -y opencv-python-headless nvidia-dali-cuda130 pyelftools
 # 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.
 RUN rm -rf /opt/pytorch/pytorch/third_party/onnx
 
-# Patch wandb-core: bump google.golang.org/grpc from 1.79.2 to 1.79.3 (CVE fix)
+# Patch wandb-core with fixed gRPC-Go and Go standard-library versions.
 ARG TARGETARCH
-RUN GRPC_VERSION=1.79.3 && \
-    GO_VERSION=1.26.1 && \
+RUN GRPC_VERSION=1.82.1 && \
+    GO_VERSION=1.26.5 && \
     WANDB_VERSION=$(python3 -c "import wandb; print(wandb.__version__)") && \
     WANDB_CORE_BIN=/opt/venv/lib/python3.12/site-packages/wandb/bin/wandb-core && \
     curl -fsSL "https://dl.google.com/go/go${GO_VERSION}.linux-${TARGETARCH}.tar.gz" | tar -C /tmp -xz && \
@@ -114,12 +117,13 @@ RUN GRPC_VERSION=1.79.3 && \
         -o "${WANDB_CORE_BIN}" ./cmd/wandb-core/ && \
     rm -rf /tmp/wandb-src /tmp/go /tmp/gopath
 
-# Patch wandb-core (dist-packages copy): bump github.com/go-git/go-git/v5 to 5.19.0 (CVE fix).
+# Patch wandb-core (dist-packages copy) with fixed go-git, gRPC-Go, and Go versions.
 # This stock upstream binary ships with go-git v5.17.2 and is a separate wandb install from the
 # /opt/venv copy rebuilt above, so it must be rebuilt against its own wandb version (resolved via
 # the system interpreter that owns dist-packages) to avoid a python/wandb-core version mismatch.
 RUN GO_GIT_VERSION=5.19.0 && \
-    GO_VERSION=1.26.1 && \
+    GRPC_VERSION=1.82.1 && \
+    GO_VERSION=1.26.5 && \
     WANDB_VERSION=$(/usr/bin/python3 -c "import wandb; print(wandb.__version__)") && \
     WANDB_CORE_BIN=/usr/local/lib/python3.12/dist-packages/wandb/bin/wandb-core && \
     curl -fsSL "https://dl.google.com/go/go${GO_VERSION}.linux-${TARGETARCH}.tar.gz" | tar -C /tmp -xz && \
@@ -128,6 +132,7 @@ RUN GO_GIT_VERSION=5.19.0 && \
     git clone --depth 1 --branch "v${WANDB_VERSION}" https://github.com/wandb/wandb.git /tmp/wandb-src && \
     cd /tmp/wandb-src/core && \
     go get github.com/go-git/go-git/v5@v${GO_GIT_VERSION} && \
+    go get google.golang.org/grpc@v${GRPC_VERSION} && \
     go mod tidy && \
     go mod vendor && \
     CGO_ENABLED=0 GOOS=linux GOARCH=${TARGETARCH} go build -trimpath -ldflags="-s -w" \

@@ -41,7 +41,7 @@ test = ["coverage>=7.8.1"]
 
 [tool.uv.sources]
 "nemo-export-deploy" = { path = "/opt/Export-Deploy", editable = true }
-"nemo-evaluator" = { path = "/opt/Evaluator", editable = true }
+"nemo-evaluator" = { path = "/opt/Evaluator/packages/nemo-evaluator", editable = true }
 "nemo-run" = { path = "/opt/Run", editable = true }
 "lightning" = { path = "stubs/lightning" }
 
@@ -67,9 +67,9 @@ override-dependencies = [
     "packaging>=25.0",
     "nvidia-pytriton>=0.7.0",
     "urllib3>=2.0.7",
-    "sh==2.2.2",
+    "sh==2.2.4",
     "jupyter-core==5.8.1",
-    "pillow==12.2.0",
+    "pillow==12.3.0",
     "protobuf==6.33.5",
     "cuda-python>=13.0.0",
     "multi-storage-client!=0.36.0",
@@ -79,7 +79,7 @@ override-dependencies = [
     "apache-tvm-ffi==0.1.11",
     "levenshtein; sys_platform == 'never'",
     "pytest==8.4.2",
-    "wandb>=0.25.0",
+    "wandb==0.27.2",
     "nvidia-lm-eval==25.11.1",
     "lilcom==1.8.1",
     "onnx==1.21.0",                             # TRT-LLM hard dependency
@@ -115,12 +115,15 @@ override-dependencies = [
     "setuptools>=82.0.0",                                # Required by vllm
     "open-clip-torch>=3.2.0",                            # Required by megatron-bridge, override nemo-toolkit's 2.24.0 constraint
     "lilcom!=1.8.2",
-    "cryptography>=43.0.0,<47",                          # Required by megatron-bridge, override nemo-run's constraint
+    "cryptography>=48.0.1,<49",                          # Required by megatron-bridge, override nemo-run's constraint
     "opencv-python; sys_platform == 'never'",            # Use the dependency from the base pytorch container
     "langchain~=1.0.0",
     "langchain-core~=1.3.3",                             # GHSA-pjwx-r37v-7724
     "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
-    "fastapi<0.139.2"                                    # 0.139.2 fails with ray 2.55.1 at least
+    "ray>=2.56.0",
+    "starlette==1.3.1",
+    "prometheus-fastapi-instrumentator>=8.0.0",          # 7.x requires starlette<1.0.0
+    "fastapi<0.139.2"                                    # 0.139.2 fails with ray serve
 ]
@@ -25,6 +25,7 @@ torch_tensorrt
 quack  # imports nvidia-cutlass-dsl MLIR libs, which dlopen libcuda at import
 peft # transitively imports optional CUDA-backed modules that dlopen libcuda
 transformer_engine # dlopens libcuda at import
+humming # Humming vLLM quantization kernels dlopen libcuda at import
 
 # Requires the libfuse system library (multi-storage-client FUSE backend; optional):
 mfusepy

@@ -42,8 +42,6 @@ SRC_DIR="$(mktemp -d)"
 apt-get update
 apt-get install -y --no-install-recommends \
     git ca-certificates build-essential autoconf automake libtool libhwloc-dev
-apt-get clean
-rm -rf /var/lib/apt/lists/*
 
 git clone --depth 1 --branch "${AWS_OFI_NCCL_VER}" \
     https://github.com/aws/aws-ofi-nccl.git "${SRC_DIR}"
@@ -63,6 +61,12 @@ make -j"$(nproc)"
 make install
 popd
 
+# The installed plugin links to libhwloc15 at runtime but does not need the
+# development headers or libltdl development files after compilation.
+apt-get purge -y libhwloc-dev libltdl-dev
+apt-get clean
+rm -rf /var/lib/apt/lists/*
+
 # Revive the ldconfig entry the base image left behind so a bare `libnccl-net.so`
 # lookup can also resolve here; EKSEnvPlugin still pins the absolute path.
 echo "${PREFIX}/lib" > /etc/ld.so.conf.d/aws-ofi-nccl.conf

diff --git a/docs/conf.py b/docs/conf.py
@@ -37,7 +37,7 @@
 project = "Megatron Bridge"
 copyright = "2026, NVIDIA Corporation"
 author = "NVIDIA Corporation"
-release = "nightly"
+release = "0.6.0"
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration

diff --git a/docs/fern/versions/nightly.yml b/docs/fern/versions/nightly.yml
@@ -298,6 +298,8 @@ navigation:
       path: ../../../skills/nemo-mbridge-multi-node-slurm/SKILL.md
     - page: Templates
       path: ../../../skills/nemo-mbridge-multi-node-slurm/references/templates.md
+    - page: Memory Snapshot Analysis
+      path: ../../../skills/nemo-mbridge-memory-snapshot-analysis/SKILL.md
     - page: Resiliency
       path: ../../../skills/nemo-mbridge-resiliency/SKILL.md
     section: Agent Skills Reference

diff --git a/docs/fern/versions/nightly/pages/training/profiling.mdx b/docs/fern/versions/nightly/pages/training/profiling.mdx
@@ -164,7 +164,13 @@ cfg.profiling = ProfilingConfig(
 
 ### Analyze Memory Usage
 
-After the run completes, memory snapshots for each specified rank are saved to the designated path. Load these traces using the PyTorch Memory Viz tool to plot memory usage over time and detect bottlenecks or leaks in your training pipeline.
+After the run completes, memory snapshots for each specified rank are saved to the designated path, with the rank inserted before the extension (for example, `memory_trace_0.pickle`). Load these traces using the PyTorch Memory Viz tool to plot memory usage over time and detect bottlenecks or leaks in your training pipeline.
+
+For comparing two runs, attributing peak memory to specific allocation sites, or drilling into a captured out-of-memory snapshot, see the Memory Snapshot Analysis skill, which bundles scripts for replaying and diffing these files.
+
+<Note>
+`record_memory_history` and `use_pytorch_profiler` are independent settings. `ProfilerStep#N` annotations inside the snapshot come from the PyTorch profiler, so a snapshot captured with `record_memory_history=True` alone contains no step boundaries. Enable both if you want per-step memory analysis.
+</Note>
 
 ## Optimize Profiling Accuracy
 

diff --git a/docs/index.md b/docs/index.md
@@ -36,10 +36,13 @@ bridge-tech-details.md
 models/README.md
 models/bailing/index.md
 models/deepseek/index.md
+models/ernie/ernie45.md
+models/exaone/exaone.md
 models/falcon/index.md
 models/gemma/index.md
 models/glm/index.md
 models/gpt_oss/index.md
+models/hy_v3/hy-v3.md
 models/kimi/index.md
 models/llama/index.md
 models/minimax/index.md

diff --git a/docs/models/README.md b/docs/models/README.md
@@ -17,10 +17,13 @@ Megatron Bridge conversion, training recipe links, and model-specific notes.
 |----------------|---------------------|
 | **Bailing** | [Ling 2.0](bailing/ling-2.md) |
 | **DeepSeek** | [DeepSeek V2 (deprecated)](deepseek/deepseek-v2.md), [DeepSeek V3](deepseek/deepseek-v3.md), [DeepSeek V4](deepseek/deepseek-v4.md) |
+| **ERNIE** | [ERNIE 4.5 and ERNIE 4.5 VL](ernie/ernie45.md) |
+| **EXAONE** | [EXAONE 4, EXAONE 4.5 VL, and K-EXAONE](exaone/exaone.md) |
 | **Falcon** | [Falcon H1](falcon/falcon-h1.md) |
 | **Gemma** | [Gemma (deprecated)](gemma/gemma.md), [Gemma 2 (deprecated)](gemma/gemma2.md), [Gemma 3](gemma/gemma3.md), [Gemma 3 VL](gemma/gemma3-vl.md), [Gemma 4 VL](gemma/gemma4-vl.md) |
-| **GLM** | [GLM 4.5](glm/glm45.md), [GLM-4.5V](glm/glm-45v.md), [GLM-4.7 / 4.7-Flash](glm/glm47.md), [GLM-5 / 5.1](glm/glm5.md) |
+| **GLM** | [GLM-4.5](glm/glm45.md), [GLM-4.5V](glm/glm-45v.md), [GLM-4.7 / GLM-4.7-Flash](glm/glm47.md), [GLM-5 / GLM-5.1 / GLM-5.2](glm/glm5.md) |
 | **GPT-OSS** | [GPT OSS](gpt_oss/gpt-oss.md) |
+| **HY V3** | [HY V3](hy_v3/hy-v3.md) |
 | **Kimi** | [Kimi K2](kimi/kimi-k2.md), [Kimi-K2.5-VL](kimi/kimi-k25-vl.md) |
 | **Llama** | [Llama 2 (deprecated)](llama/llama2.md), [Llama 3](llama/llama3.md) |
 | **MiniMax** | [MiniMax-M2 / M2.5 / M2.7](minimax/minimax-m2.md), [MiniMax-M3](minimax/minimax-m3.md) |
@@ -65,12 +68,13 @@ Each model documentation page typically includes:
 
 ### Decoder-Only and Hybrid Backbones
 
-- Bailing, DeepSeek, Falcon, Gemma, GLM, GPT-OSS, Kimi, Llama, MiniMax, Mistral, Moonlight, Nemotron, OLMoE, Qwen, Sarvam, StepFun, and Xiaomi-MiMo
+- Bailing, DeepSeek, ERNIE, EXAONE, Falcon, Gemma, GLM, GPT-OSS, HY V3, Kimi, Llama, MiniMax, Mistral, Moonlight, Nemotron, OLMoE, Qwen, Sarvam, StepFun, and Xiaomi-MiMo
 - MoE and hybrid variants including Bailing, DeepSeek, GLM, GPT-OSS, MiniMax, Nemotron-3, OLMoE, Qwen3-MoE, Qwen3-Next, and Sarvam
 
 ### Multimodal Variants
 
 - Gemma 3 VL and Gemma 4 VL
+- ERNIE 4.5 VL and EXAONE 4.5 VL
 - GLM-4.5V
 - Kimi-K2.5-VL
 - Ministral 3

diff --git a/docs/models/ernie/ernie45.md b/docs/models/ernie/ernie45.md
@@ -0,0 +1,20 @@
+# ERNIE 4.5
+
+Megatron Bridge registers Hugging Face conversion support for the text-only
+`baidu/ERNIE-4.5-0.3B-PT` MoE model and the
+`baidu/ERNIE-4.5-VL-28B-A3B-Instruct` and `baidu/ERNIE-4.5-VL-28B-A3B-Thinking`
+vision-language MoE models.
+
+Import a text checkpoint with the shared conversion CLI:
+
+```bash
+./scripts/conversion/convert.sh import \
+  --hf-model baidu/ERNIE-4.5-0.3B-PT \
+  --megatron-path /workspace/models/ernie-4.5-0.3b \
+  --trust-remote-code
+```
+
+For ERNIE 4.5 VL import, export, and inference commands, see the
+[checked-in examples](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/vlm/ernie_vl).
+The VL bridge supports its modality-specific dual-pool MoE layout; use the
+parallelism settings documented with those examples.
diff --git a/docs/models/exaone/exaone.md b/docs/models/exaone/exaone.md
@@ -0,0 +1,18 @@
+# EXAONE
+
+Megatron Bridge supports Hugging Face conversion for EXAONE 4.0 dense language
+models, EXAONE 4.5 vision-language models, and K-EXAONE MoE language models.
+Checked-in H100 recipes cover EXAONE 4.0 1.2B, EXAONE 4.5 VL 33B,
+K-EXAONE-236B-A23B, and K-EXAONE 2.0 750B-A37B.
+
+Use the model-specific examples for commands and supported parallelism:
+
+- [EXAONE 4.0](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/exaone/exaone4)
+- [EXAONE 4.5 VL](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/exaone/exaone45)
+- [K-EXAONE MoE](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/exaone/exaone_moe)
+
+The EXAONE 4.0 and EXAONE 4.5 examples use the shared
+`scripts/conversion/convert.sh import` entry point. The K-EXAONE examples use
+their model-specific distributed round-trip workflows. K-EXAONE 2.0 also has a checked-in
+[model verification card](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/model_verification_cards/k-exaone-2/card.yaml)
+that records the current verification status of individual workflows.
diff --git a/docs/models/glm/glm5.md b/docs/models/glm/glm5.md
@@ -1,13 +1,14 @@
-# GLM-5 and GLM-5.1
+# GLM-5, GLM-5.1, and GLM-5.2
 
-[GLM-5](https://huggingface.co/zai-org/GLM-5) and [GLM-5.1](https://huggingface.co/zai-org/GLM-5.1) are large sparse MoE language models with Multi-Latent Attention and Dynamic Sparse Attention. Megatron Bridge supports both checkpoints through the shared `GLM5Bridge`.
+[GLM-5](https://huggingface.co/zai-org/GLM-5), [GLM-5.1](https://huggingface.co/zai-org/GLM-5.1), and [GLM-5.2](https://huggingface.co/zai-org/GLM-5.2) are large sparse MoE language models with Multi-Latent Attention and Dynamic Sparse Attention. Megatron Bridge supports these checkpoints through the shared `GLM5Bridge`.
 
 ## Supported Variants
 
 | Variant | Hugging Face ID | Notes |
 |---------|-----------------|-------|
 | GLM-5 | `zai-org/GLM-5` | MoE + MLA + DSA architecture |
 | GLM-5.1 | `zai-org/GLM-5.1` | Same architecture and mapping shape as GLM-5 |
+| GLM-5.2 | `zai-org/GLM-5.2` | Adds IndexShare-style DSA index reuse settings |
 
 ## Architecture Notes
 
@@ -20,10 +21,9 @@
 
 ## Examples
 
-For conversion, inference, dependency notes, hardware requirements, and MCore patch requirements, see the [GLM-5 examples README](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/glm/glm5/README.md).
+For the pinned checkpoint revision, tested topology, commands, and expected results for verified GLM-5.2 workflows, see the [GLM-5.2 model verification card](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/model_verification_cards/glm5-2/card.yaml). For the GLM-5 conversion wrapper, dependency notes, and architecture constraints, see the [GLM-5 examples README](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/glm/glm5/README.md).
 
 ## Related Implementation
 
 - Bridge implementation: [`src/megatron/bridge/models/glm_moe_dsa/glm5_bridge.py`](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/src/megatron/bridge/models/glm_moe_dsa/glm5_bridge.py)
 - Examples: [`examples/models/glm/glm5`](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/models/glm/glm5)
-
diff --git a/docs/models/glm/index.md b/docs/models/glm/index.md
@@ -13,7 +13,7 @@ glm5.md
 
 | Variant | Guide |
 |---------|-------|
-| GLM 4.5 | [glm45.md](glm45.md) |
+| GLM-4.5 | [glm45.md](glm45.md) |
 | GLM-4.5V | [glm-45v.md](glm-45v.md) |
-| GLM-4.7 / 4.7-Flash | [glm47.md](glm47.md) |
-| GLM-5 / 5.1 | [glm5.md](glm5.md) |
+| GLM-4.7 / GLM-4.7-Flash | [glm47.md](glm47.md) |
+| GLM-5 / GLM-5.1 / GLM-5.2 | [glm5.md](glm5.md) |
diff --git a/docs/models/hy_v3/hy-v3.md b/docs/models/hy_v3/hy-v3.md
@@ -0,0 +1,27 @@
+# HY V3
+
+Megatron Bridge registers Hugging Face checkpoint conversion for the
+`tencent/Hy3-preview-Base` MoE causal language model. The bridge maps HY V3's
+GQA with QK layer normalization, dense-first layer schedule, sigmoid router,
+shared experts, and grouped-GEMM routed experts to Megatron Core.
+
+Import the checkpoint with the shared conversion CLI:
+
+```bash
+./scripts/conversion/convert.sh import \
+  --hf-model tencent/Hy3-preview-Base \
+  --megatron-path /workspace/models/hy3-preview-base \
+  --trust-remote-code
+```
+
+Export a converted checkpoint back to Hugging Face format:
+
+```bash
+./scripts/conversion/convert.sh export \
+  --hf-model tencent/Hy3-preview-Base \
+  --megatron-path /workspace/models/hy3-preview-base/iter_0000000 \
+  --hf-path /workspace/models/hy3-preview-base-hf \
+  --trust-remote-code
+```
+
+No library training recipe is currently exported for HY V3.
diff --git a/docs/models/mimo/mimo.md b/docs/models/mimo/mimo.md
@@ -18,6 +18,7 @@ Megatron Bridge supports Hugging Face checkpoints using the `MiMoForCausalLM` ar
 Checkpoint conversion and text-generation examples for MiMo causal language
 models live under
 [`examples/models/mimo`](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/6a706b1c3afab4d21a6f5dd88aa6a75296d33fe2/examples/models/mimo/README.md).
+For MiMo-V2-Flash conversion and inference examples, see the [MiMo-V2-Flash examples README](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/mimo_v2_flash/README.md).
 Heterogeneous multimodal training examples live separately under
 [`examples/megatron_mimo`](https://github.com/NVIDIA-NeMo/Megatron-Bridge/tree/main/examples/megatron_mimo).
 

diff --git a/docs/models/stepfun/step35.md b/docs/models/stepfun/step35.md
@@ -17,6 +17,7 @@
 ## Examples
 
 For conversion, inference, pretraining, Slurm launch scripts, and MCore branch notes, see the [Step-3.5-Flash examples README](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/stepfun/step35/README.md).
+For Step 3.7 Flash conversion and training examples, see the [Step 3.7 Flash examples README](https://github.com/NVIDIA-NeMo/Megatron-Bridge/blob/main/examples/models/stepfun/step37/README.md).
 
 ## Related Implementation
Original file line number	Diff line number	Diff line change
		@@ -1 +1 @@
		0e6ac576fba8995fca541ceb6af5f35eb0e4f16e
		43e45e13074f36da68b34c7a189cd997a01d1b41