THUDM · zhuzilin · Mar 11, 2026 · Mar 11, 2026
diff --git a/docs/en/examples/glm4.7-30B-A3B.md b/docs/en/examples/glm4.7-30B-A3B.md
@@ -5,6 +5,14 @@
 
 The environment setup, data, and checkpoint conversion are the same as for the Qwen3-4B model. You can refer to [Example: Qwen3-4B Model](qwen3-4B.md), replacing mentions of Qwen3-4B with GLM-4.7-Flash.
 
+### Prerequisites
+
+GLM-4.7-Flash requires **transformers ≥ 5.0** for the `Glm4MoeLiteForCausalLM` architecture. Install or upgrade:
+
+```bash
+pip install "transformers>=5.0"
+```
+
 ### Download Model
 
 ```bash
@@ -119,9 +127,9 @@ SPEC_ARGS=(
 - `--enable-mtp-training`: Enables gradient computation for MTP layers. Without this flag, the MTP layer is loaded but frozen.
 - `--mtp-loss-scaling-factor 0.2`: Weight of the MTP loss relative to the main policy loss. Default is 0.2.
 
-> ⚠️ **Note**: MTP training for GLM-4.7-Flash is not yet supported because the deepseek_v3 checkpoint bridge does not include MTP weight conversion (`# TODO: mtp` in upstream mbridge). You can still use MTP for speculative decoding during inference — SGLang handles MTP layers internally.
+> **Note**: MTP training requires the MTP checkpoint bridge to properly convert weights between HuggingFace and Megatron formats. The `GLM4MoELiteBridge` (in `slime_plugins/mbridge/glm4moe_lite.py`) extends the DeepSeek V3 bridge with dynamic MTP layer indexing to support GLM-4.7-Flash's 47-layer architecture.
 >
-> For models with full MTP training support (e.g., MiMo), see `scripts/run-mimo-7B-rl-eagle.sh` as a reference.
+> For other models with MTP training support (e.g., MiMo), see `scripts/run-mimo-7B-rl-eagle.sh` as a reference.
 
 ### Multi-Node Support
 

diff --git a/docs/zh/examples/glm4.7-30B-A3B.md b/docs/zh/examples/glm4.7-30B-A3B.md
@@ -4,6 +4,14 @@
 
 搭建环境、数据与 ckpt 转换均与 Qwen3-4B 模型相同，可以参考 [示例：Qwen3-4B](qwen3-4B.md)，将文中 Qwen3-4B 的部分转换为 GLM-4.7-Flash 即可。
 
+### 前置条件
+
+GLM-4.7-Flash 需要 **transformers ≥ 5.0** 以支持 `Glm4MoeLiteForCausalLM` 架构。请安装或升级：
+
+```bash
+pip install "transformers>=5.0"
+```
+
 ### 下载模型
 
 ```bash
@@ -118,9 +126,9 @@ SPEC_ARGS=(
 - `--enable-mtp-training`：启用 MTP 层的梯度计算。不设置此标志时，MTP 层会被加载但冻结。
 - `--mtp-loss-scaling-factor 0.2`：MTP loss 相对于主策略 loss 的权重，默认为 0.2。
 
-> ⚠️ **注意**：GLM-4.7-Flash 的 MTP 训练目前尚不支持，因为 deepseek_v3 的 checkpoint bridge 尚未实现 MTP 权重转换（上游 mbridge 中标注为 `# TODO: mtp`）。但推理时的投机解码仍然可用 — SGLang 会内部处理 MTP 层。
+> **注意**：MTP 训练需要 MTP checkpoint bridge 正确转换 HuggingFace 和 Megatron 格式之间的权重。`GLM4MoELiteBridge`（位于 `slime_plugins/mbridge/glm4moe_lite.py`）扩展了 DeepSeek V3 bridge，实现了动态 MTP 层索引以支持 GLM-4.7-Flash 的 47 层架构。
 >
-> 对于完整支持 MTP 训练的模型（如 MiMo），可参考 `scripts/run-mimo-7B-rl-eagle.sh`。
+> 对于其他支持 MTP 训练的模型（如 MiMo），可参考 `scripts/run-mimo-7B-rl-eagle.sh`。
 
 ### 多机支持
 

diff --git a/scripts/run-glm4.7-30B-A3B-8gpus.sh b/scripts/run-glm4.7-30B-A3B-8gpus.sh
diff --git a/scripts/run-glm4.7-30B-A3B.sh b/scripts/run-glm4.7-30B-A3B.sh
@@ -42,7 +42,6 @@ ROLLOUT_ARGS=(
 
    --num-rollout 3000
    --rollout-batch-size 128
-   #--over-sampling-batch-size 256
    --n-samples-per-prompt 8
    --rollout-max-response-len 32768
    --rollout-temperature 1.0
@@ -56,14 +55,14 @@ EVAL_ARGS=(
    --eval-prompt-data aime24 $BASE_DIR/rl_data/aime-2024.jsonl
    --n-samples-per-eval-prompt 2
    --eval-max-response-len 16384
-   --eval-temperature 0.6
+   --eval-temperature 1.0
    --eval-top-p 0.95
 )
 
 PERF_ARGS=(
    --tensor-model-parallel-size 4
    --sequence-parallel
-   --pipeline-model-parallel-size 2
+   --pipeline-model-parallel-size 1
    --context-parallel-size 2
    --expert-model-parallel-size 8
    --expert-tensor-parallel-size 1
@@ -77,6 +76,12 @@ PERF_ARGS=(
    --max-tokens-per-gpu 32768
 )
 
+MTP_ARGS=(
+   --mtp-num-layers 1
+   --enable-mtp-training
+   --mtp-loss-scaling-factor 0.2
+)
+
 GRPO_ARGS=(
    --advantage-estimator grpo
    --use-kl-loss
@@ -139,56 +144,24 @@ MISC_ARGS=(
 )
 
 # launch the master node of ray in container
-export MASTER_ADDR=${MLP_WORKER_0_HOST}
-export no_proxy="127.0.0.1,${MASTER_ADDR}"
-ray start --head --node-ip-address ${MASTER_ADDR} --num-gpus 8 --disable-usage-stats
-
-for WORKER_IP in $(awk '{print $1}' /root/mpi_rack_hostfile); do
-  if [[ "$WORKER_IP" == "$MLP_WORKER_0_HOST" ]]; then
-    continue
-  fi
-  echo "Starting Ray worker on ${WORKER_IP}"
-  ssh root@"${WORKER_IP}" \
-    "pkill -9 sglang ; ray stop --force ; pkill -9 python ; ray start --address=${MASTER_ADDR}:6379 --num-gpus 8 --node-ip-address ${WORKER_IP} --disable-usage-stats" &
-done
-wait
+export MASTER_ADDR=${MASTER_ADDR:-"127.0.0.1"}
+ray start --head --node-ip-address ${MASTER_ADDR} --num-gpus 8 --disable-usage-stats --dashboard-host=0.0.0.0 --dashboard-port=8265
+
+# Build the runtime environment JSON with proper variable substitution
+RUNTIME_ENV_JSON="{
+  \"env_vars\": {
+    \"PYTHONPATH\": \"/root/Megatron-LM/\",
+    \"CUDA_DEVICE_MAX_CONNECTIONS\": \"1\",
+    \"NCCL_NVLS_ENABLE\": \"${HAS_NVLINK}\"
+  }
+}"
 
 ray job submit --address="http://127.0.0.1:8265" \
-   --runtime-env-json='{
-     "env_vars": {
-        "no_proxy": "localhost,127.0.0.1,0.0.0.0,${MASTER_ADDR}",
-        "GLOO_SOCKET_IFNAME": "${MLP_SOCKET_IFNAME}",
-        "TP_SOCKET_IFNAME": "${MLP_SOCKET_IFNAME}",
-        "MASTER_ADDR": "${MLP_WORKER_0_HOST}",
-        "PYTHONPATH": "/root/Megatron-LM/",
-        "NCCL_CUMEM_ENABLE": "0",
-        "CUDA_DEVICE_MAX_CONNECTIONS": "1",
-        "NVTE_BWD_LAYERNORM_SM_MARGIN": "20",
-        "NCCL_IB_TC": "160",
-        "NCCL_PXN_DISABLE": "0",
-        "NCCL_IB_GID_INDEX": "3",
-        "NCCL_NET_GDR_LEVEL": "4",
-        "NCCL_IB_RETRY_CNT": "7",
-        "NCCL_IB_TIMEOUT": "32",
-        "NCCL_IB_QPS_PER_CONNECTION": "8",
-        "NCCL_P2P_LEVEL": "NVL",
-        "TORCH_NCCL_AVOID_RECORD_STREAMS": "1",
-        "NCCL_NVLS_ENABLE": "0",
-        "NCCL_MIN_CTAS": "4",
-        "OMPI_MCA_pml": "ob1",
-        "OMPI_MCA_btl": "^openib",
-        "OMPI_MCA_routed": "direct",
-        "OMPI_MCA_routed_radix": "1024",
-        "OMPI_MCA_plm_rsh_no_tree_spawn": "1",
-        "OMPI_MCA_oob_tcp_if_include": "${MLP_SOCKET_IFNAME}",
-        "OMPI_MCA_btl_tcp_if_include": "${MLP_SOCKET_IFNAME}"
-     }
-   }' \
+   --runtime-env-json="${RUNTIME_ENV_JSON}" \
    -- python3 train.py \
-   --actor-num-nodes 2 \
+   --actor-num-nodes 1 \
    --actor-num-gpus-per-node 8 \
    --colocate \
-   --save-debug-rollout-data "data.pt" \
    ${MODEL_ARGS[@]} \
    ${CKPT_ARGS[@]} \
    ${ROLLOUT_ARGS[@]} \
@@ -198,4 +171,5 @@ ray job submit --address="http://127.0.0.1:8265" \
    ${PERF_ARGS[@]} \
    ${EVAL_ARGS[@]} \
    ${SGLANG_ARGS[@]} \
-   ${MISC_ARGS[@]}
+   ${MISC_ARGS[@]} \
+   ${MTP_ARGS[@]}
diff --git a/slime/backends/megatron_utils/model_provider.py b/slime/backends/megatron_utils/model_provider.py
@@ -96,6 +96,20 @@ def wrapped_model_provider(
         if getattr(args, "decoder_last_pipeline_num_layers", None) is not None:
             provider.num_layers_in_last_pipeline_stage = args.decoder_last_pipeline_num_layers
         provider.finalize()
+
+        if role == "critic":
+            _original_provide = provider.provide
+
+            def _critic_provide(pre_process=True, post_process=True, vp_stage=None):
+                model = _original_provide(pre_process=pre_process, post_process=post_process, vp_stage=vp_stage)
+                if post_process:
+                    model.output_layer = LinearForLastLayer(
+                        input_size=model.config.hidden_size, output_size=1, config=model.config
+                    )
+                return model
+
+            return _critic_provide
+
         return provider.provide
 
     def model_provider(pre_process: bool = True, post_process: bool = True, vp_stage: int | None = None) -> GPTModel: