[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QG2EXPP1ZBXXVZP379VAA5":3,"skill-same:01M6QG2EXPP1ZBXXVZP379VAA5":83},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":14,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6QG2EXPP1ZBXXVZP379VAA5","slime-rl-training",null,"Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.","Tashima-Tarsh\u002FDisha6.6","Tashima-Tarsh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269906498?v=4","01M6PBH98X03XERH0HFT4PFB1P","NITISH KUMAR","01M6PBH9DA0M6KM3Z12P848F0K",0,"MIT","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-slime-rl-training\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"training","slime","slime rl training","rl","GRPO","Post-Training","Ray","learning","use","router","integration","models","reinforcement learning","reinforcement","workflows","post","megatron","implementing","for","custom","2026-11-10 10:12:30",false,"---\nname: slime-rl-training\ndescription: Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  category: ml-training\n  maintainer: Kalaris Labs\n  tags: Reinforcement Learning, Megatron-LM, SGLang, GRPO, Post-Training, GLM\n  dependencies: sglang-router>=0.2.3, ray, torch>=2.0.0, transformers>=4.40.0\n---\n\n# slime: LLM Post-Training Framework for RL Scaling\n\nslime is an LLM post-training framework from Tsinghua's THUDM team, powering GLM-4.5, GLM-4.6, and GLM-4.7. It connects Megatron-LM for training with SGLang for high-throughput rollout generation.\n\n## When to Use slime\n\n**Choose slime when you need:**\n- Megatron-LM native training with SGLang inference\n- Custom data generation workflows with flexible data buffers\n- Training GLM, Qwen3, DeepSeek V3, or Llama 3 models\n- Research-grade framework with production backing (Z.ai)\n\n**Consider alternatives when:**\n- You need enterprise-grade stability features → use **miles**\n- You want flexible backend swapping → use **verl**\n- You need PyTorch-native abstractions → use **torchforge**\n\n## Key Features\n\n- **Training**: Megatron-LM with full parallelism support (TP, PP, DP, SP)\n- **Rollout**: SGLang-based high-throughput generation with router\n- **Data Buffer**: Flexible prompt management and sample storage\n- **Models**: GLM-4.x, Qwen3, DeepSeek V3\u002FR1, Llama 3\n\n## Architecture Overview\n\n```\n┌─────────────────────────────────────────────────────────┐\n│                    Data Buffer                          │\n│ - Prompt initialization and management                  │\n│ - Custom data generation and filtering                  │\n│ - Rollout sample storage                                │\n└─────────────┬───────────────────────────┬───────────────┘\n              │                           │\n┌─────────────▼───────────┐ ┌─────────────▼───────────────┐\n│ Training (Megatron-LM)  │ │ Rollout (SGLang + Router)   │\n│ - Actor model training  │ │ - Response generation       │\n│ - Critic (optional)     │ │ - Reward\u002Fverifier output    │\n│ - Weight sync to rollout│ │ - Multi-turn support        │\n└─────────────────────────┘ └─────────────────────────────┘\n```\n\n## Installation\n\n```bash\n# Recommended: Docker\ndocker pull slimerl\u002Fslime:latest\ndocker run --rm --gpus all --ipc=host --shm-size=16g \\\n  -it slimerl\u002Fslime:latest \u002Fbin\u002Fbash\n\n# Inside container\ncd \u002Froot\u002Fslime && pip install -e . --no-deps\n```\n\n### From Source\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FTHUDM\u002Fslime.git\ncd slime\npip install -r requirements.txt\npip install -e .\n```\n\n## Quick Start: GRPO Training\n\n```bash\n# Source model configuration\nsource scripts\u002Fmodels\u002Fqwen3-4B.sh\n\n# Launch training\npython train.py \\\n    --actor-num-nodes 1 \\\n    --actor-num-gpus-per-node 4 \\\n    --rollout-num-gpus 4 \\\n    --advantage-estimator grpo \\\n    --use-kl-loss --kl-loss-coef 0.001 \\\n    --rollout-batch-size 32 \\\n    --n-samples-per-prompt 8 \\\n    --global-batch-size 256 \\\n    --num-rollout 3000 \\\n    --prompt-data \u002Fpath\u002Fto\u002Fdata.jsonl \\\n    ${MODEL_ARGS[@]} ${CKPT_ARGS[@]}\n```\n\n---\n\n## Workflow 1: Standard GRPO Training\n\nUse this workflow for training reasoning models with group-relative advantages.\n\n### Prerequisites Checklist\n- [ ] Docker environment or Megatron-LM + SGLang installed\n- [ ] Model checkpoint (HuggingFace or Megatron format)\n- [ ] Training data in JSONL format\n\n### Step 1: Prepare Data\n\n```python\n# data.jsonl format\n{\"prompt\": \"What is 2 + 2?\", \"label\": \"4\"}\n{\"prompt\": \"Solve: 3x = 12\", \"label\": \"x = 4\"}\n```\n\nOr with chat format:\n```python\n{\n    \"prompt\": [\n        {\"role\": \"system\", \"content\": \"You are a math tutor.\"},\n        {\"role\": \"user\", \"content\": \"What is 15 + 27?\"}\n    ],\n    \"label\": \"42\"\n}\n```\n\n### Step 2: Configure Model\n\nChoose a pre-configured model script:\n\n```bash\n# List available models\nls scripts\u002Fmodels\u002F\n# glm4-9B.sh, qwen3-4B.sh, qwen3-30B-A3B.sh, deepseek-v3.sh, llama3-8B.sh, ...\n\n# Source your model\nsource scripts\u002Fmodels\u002Fqwen3-4B.sh\n```\n\n### Step 3: Launch Training\n\n```bash\npython train.py \\\n    --actor-num-nodes 1 \\\n    --actor-num-gpus-per-node 8 \\\n    --rollout-num-gpus 8 \\\n    --advantage-estimator grpo \\\n    --use-kl-loss \\\n    --kl-loss-coef 0.001 \\\n    --prompt-data \u002Fpath\u002Fto\u002Ftrain.jsonl \\\n    --input-key prompt \\\n    --label-key label \\\n    --apply-chat-template \\\n    --rollout-batch-size 32 \\\n    --n-samples-per-prompt 8 \\\n    --global-batch-size 256 \\\n    --num-rollout 3000 \\\n    --save-interval 100 \\\n    --eval-interval 50 \\\n    ${MODEL_ARGS[@]}\n```\n\n### Step 4: Monitor Training\n- [ ] Check TensorBoard: `tensorboard --logdir outputs\u002F`\n- [ ] Verify reward curves are increasing\n- [ ] Monitor GPU utilization across nodes\n\n---\n\n## Workflow 2: Asynchronous Training\n\nUse async mode for higher throughput by overlapping rollout and training.\n\n### When to Use Async\n- Large models with long generation times\n- High GPU idle time in synchronous mode\n- Sufficient memory for buffering\n\n### Launch Async Training\n\n```bash\npython train_async.py \\\n    --actor-num-nodes 1 \\\n    --actor-num-gpus-per-node 8 \\\n    --rollout-num-gpus 8 \\\n    --advantage-estimator grpo \\\n    --async-buffer-size 4 \\\n    --prompt-data \u002Fpath\u002Fto\u002Ftrain.jsonl \\\n    ${MODEL_ARGS[@]}\n```\n\n### Async-Specific Parameters\n\n```bash\n--async-buffer-size 4        # Number of rollouts to buffer\n--update-weights-interval 2  # Sync weights every N rollouts\n```\n\n---\n\n## Workflow 3: Multi-Turn Agentic Training\n\nUse this workflow for training agents with tool use or multi-step reasoning.\n\n### Prerequisites\n- [ ] Custom generate function for multi-turn logic\n- [ ] Tool\u002Fenvironment interface\n\n### Step 1: Define Custom Generate Function\n\n```python\n# custom_generate.py\nasync def custom_generate(args, samples, evaluation=False):\n    \"\"\"Multi-turn generation with tool calling.\"\"\"\n    for sample in samples:\n        conversation = sample.prompt\n\n        for turn in range(args.max_turns):\n            # Generate response\n            response = await generate_single(conversation)\n\n            # Check for tool call\n            tool_call = extract_tool_call(response)\n            if tool_call:\n                tool_result = execute_tool(tool_call)\n                conversation.append({\"role\": \"assistant\", \"content\": response})\n                conversation.append({\"role\": \"tool\", \"content\": tool_result})\n            else:\n                break\n\n        sample.response = response\n        sample.reward = compute_reward(sample)\n\n    return samples\n```\n\n### Step 2: Launch with Custom Function\n\n```bash\npython train.py \\\n    --custom-generate-function-path custom_generate.py \\\n    --max-turns 5 \\\n    --prompt-data \u002Fpath\u002Fto\u002Fagent_data.jsonl \\\n    ${MODEL_ARGS[@]}\n```\n\nSee `examples\u002Fsearch-r1\u002F` for a complete multi-turn search example.\n\n---\n\n## Configuration Reference\n\n### Three Argument Categories\n\nslime uses three types of arguments:\n\n**1. Megatron Arguments** (passed directly):\n```bash\n--tensor-model-parallel-size 2\n--pipeline-model-parallel-size 1\n--num-layers 32\n--hidden-size 4096\n```\n\n**2. SGLang Arguments** (prefixed with `--sglang-`):\n```bash\n--sglang-mem-fraction-static 0.8\n--sglang-context-length 8192\n--sglang-log-level INFO\n```\n\n**3. slime Arguments**:\n```bash\n# Resource allocation\n--actor-num-nodes 1\n--actor-num-gpus-per-node 8\n--rollout-num-gpus 8\n--colocate  # Share GPUs between training\u002Finference\n\n# Data\n--prompt-data \u002Fpath\u002Fto\u002Fdata.jsonl\n--input-key prompt\n--label-key label\n\n# Training loop\n--num-rollout 3000\n--rollout-batch-size 32\n--n-samples-per-prompt 8\n--global-batch-size 256\n\n# Algorithm\n--advantage-estimator grpo  # or: gspo, ppo, reinforce_plus_plus\n--use-kl-loss\n--kl-loss-coef 0.001\n```\n\n### Key Constraints\n\n```\nrollout_batch_size × n_samples_per_prompt = global_batch_size × num_steps_per_rollout\n```\n\nExample: 32 × 8 = 256 × 1\n\n---\n\n## Data Buffer System\n\nslime's data buffer enables flexible data management:\n\n### Basic Data Source\n\n```python\nclass RolloutDataSource:\n    def get_samples(self, num_samples):\n        \"\"\"Fetch prompts from dataset.\"\"\"\n        return self.dataset.sample(num_samples)\n\n    def add_samples(self, samples):\n        \"\"\"Called after generation (no-op by default).\"\"\"\n        pass\n```\n\n### Buffered Data Source (Off-Policy)\n\n```python\nclass RolloutDataSourceWithBuffer(RolloutDataSource):\n    def __init__(self):\n        self.buffer = []\n\n    def add_samples(self, samples):\n        \"\"\"Store generated samples for reuse.\"\"\"\n        self.buffer.extend(samples)\n\n    def buffer_filter(self, args, buffer, num_samples):\n        \"\"\"Custom selection logic (prioritized, stratified, etc.).\"\"\"\n        return select_best(buffer, num_samples)\n```\n\n---\n\n## Common Issues and Solutions\n\n### Issue: SGLang Engine Crash\n\n**Symptoms**: Inference engine dies mid-training\n\n**Solutions**:\n```bash\n# Enable fault tolerance\n--use-fault-tolerance\n\n# Increase memory allocation\n--sglang-mem-fraction-static 0.85\n\n# Reduce batch size\n--rollout-batch-size 16\n```\n\n### Issue: Weight Sync Timeout\n\n**Symptoms**: Training hangs after rollout\n\n**Solutions**:\n```bash\n# Increase sync interval\n--update-weights-interval 5\n\n# Use colocated mode (no network transfer)\n--colocate\n```\n\n### Issue: OOM During Training\n\n**Symptoms**: CUDA OOM in backward pass\n\n**Solutions**:\n```bash\n# Enable gradient checkpointing\n--recompute-activations\n\n# Reduce micro-batch size\n--micro-batch-size 1\n\n# Enable sequence parallelism\n--sequence-parallel\n```\n\n### Issue: Slow Data Loading\n\n**Symptoms**: GPU idle during data fetch\n\n**Solutions**:\n```bash\n# Increase data workers\n--num-data-workers 4\n\n# Use streaming dataset\n--streaming-data\n```\n\n---\n\n## Supported Models\n\n| Model Family | Configurations |\n|--------------|----------------|\n| GLM | GLM-4.5, GLM-4.6, GLM-4.7, GLM-Z1-9B |\n| Qwen | Qwen3 (4B, 8B, 30B-A3B), Qwen3-MoE, Qwen2.5 |\n| DeepSeek | V3, V3.1, R1 |\n| Llama | Llama 3 (8B, 70B) |\n| Others | Kimi K2, Moonlight-16B |\n\nEach model has pre-configured scripts in `scripts\u002Fmodels\u002F`.\n\n---\n\n## Advanced Topics\n\n### Co-location Mode\n\nShare GPUs between training and inference to reduce memory:\n\n```bash\npython train.py \\\n    --colocate \\\n    --actor-num-gpus-per-node 8 \\\n    --sglang-mem-fraction-static 0.4 \\\n    ${MODEL_ARGS[@]}\n```\n\n### Custom Reward Model\n\n```python\n# custom_rm.py\nclass CustomRewardModel:\n    def __init__(self, model_path):\n        self.model = load_model(model_path)\n\n    def compute_reward(self, prompts, responses):\n        inputs = self.tokenize(prompts, responses)\n        scores = self.model(inputs)\n        return scores.tolist()\n```\n\n```bash\n--custom-rm-path custom_rm.py\n```\n\n### Evaluation Multi-Task\n\n```bash\n--eval-prompt-data aime \u002Fpath\u002Fto\u002Faime.jsonl \\\n--eval-prompt-data gsm8k \u002Fpath\u002Fto\u002Fgsm8k.jsonl \\\n--n-samples-per-eval-prompt 16\n```\n\n---\n\n## Resources\n\n- **Documentation**: https:\u002F\u002Fthudm.github.io\u002Fslime\u002F\n- **GitHub**: https:\u002F\u002Fgithub.com\u002FTHUDM\u002Fslime\n- **Blog**: https:\u002F\u002Flmsys.org\u002Fblog\u002F2025-07-09-slime\u002F\n- **Examples**: See `examples\u002F` directory for 14+ worked examples\n\n## Agent operating procedure\n\n1. **Check the environment.** Check GPU type, memory and driver\u002FCUDA versions (`nvidia-smi`), framework versions, and dataset location and size.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Do a smoke run: tiny model or subset, few steps, and confirm loss decreases and checkpoints save.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Track metrics on held-out data, compare against a baseline, and record seeds, configs and hardware.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| CUDA out-of-memory | Reduce batch size, enable gradient accumulation\u002Fcheckpointing or mixed precision, or shard the model. |\n| Loss is NaN or diverges | Lower the learning rate, check data for invalid values, and enable gradient clipping. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Never claim training results without logs; estimate compute cost before launching large jobs.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `verl-rl-training`: Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL).\n- `miles-rl-training`: Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime.\n- `nanogpt`: Provides nanoGPT, Karpathy's minimal PyTorch GPT implementation (model.py and train.py), with workflows for training character-level Shakes…\n","# slime: LLM Post-Training Framework for RL Scaling\n\nslime is an LLM post-training framework from Tsinghua's THUDM team, powering GLM-4.5, GLM-4.6, and GLM-4.7. It connects Megatron-LM for training with SGLang for high-throughput rollout generation.\n\n## When to Use slime\n\n**Choose slime when you need:**\n- Megatron-LM native training with SGLang inference\n- Custom data generation workflows with flexible data buffers\n- Training GLM, Qwen3, DeepSeek V3, or Llama 3 models\n- Research-grade framework with production backing (Z.ai)\n\n**Consider alternatives when:**\n- You need enterprise-grade stability features → use **miles**\n- You want flexible backend swapping → use **verl**\n- You need PyTorch-native abstractions → use **torchforge**\n\n## Key Features\n\n- **Training**: Megatron-LM with full parallelism support (TP, PP, DP, SP)\n- **Rollout**: SGLang-based high-throughput generation with router\n- **Data Buffer**: Flexible prompt management and sample storage\n- **Models**: GLM-4.x, Qwen3, DeepSeek V3\u002FR1, Llama 3\n\n## Architecture Overview\n\n```\n┌─────────────────────────────────────────────────────────┐\n│                    Data Buffer                          │\n│ - Prompt initialization and management                  │\n│ - Custom data generation and filtering                  │\n│ - Rollout sample storage                                │\n└─────────────┬───────────────────────────┬───────────────┘\n              │                           │\n┌─────────────▼───────────┐ ┌─────────────▼───────────────┐\n│ Training (Megatron-LM)  │ │ Rollout (SGLang + Router)   │\n│ - Actor model training  │ │ - Response generation       │\n│ - Critic (optional)     │ │ - Reward\u002Fverifier output    │\n│ - Weight sync to rollout│ │ - Multi-turn support        │\n└─────────────────────────┘ └─────────────────────────────┘\n```\n\n## Installation\n\n```bash\n# Recommended: Docker\ndocker pull slimerl\u002Fslime:latest\ndocker run --rm --gpus all --ipc=host --shm-size=16g \\\n  -it slimerl\u002Fslime:latest \u002Fbin\u002Fbash\n\n# Inside container\ncd \u002Froot\u002Fslime && pip install -e . --no-deps\n```\n\n### From Source\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FTHUDM\u002Fslime.git\ncd slime\npip install -r requirements.txt\npip install -e .\n```\n\n## Quick Start: GRPO Training\n\n```bash\n# Source model configuration\nsource scripts\u002Fmodels\u002Fqwen3-4B.sh\n\n# Launch training\npython train.py \\\n    --actor-num-nodes 1 \\\n    --actor-num-gpus-per-node 4 \\\n    --rollout-num-gpus 4 \\\n    --advantage-estimator grpo \\\n    --use-kl-loss --kl-loss-coef 0.001 \\\n    --rollout-batch-size 32 \\\n    --n-samples-per-prompt 8 \\\n    --global-batch-size 256 \\\n    --num-rollout 3000 \\\n    --prompt-data \u002Fpath\u002Fto\u002Fdata.jsonl \\\n    ${MODEL_ARGS[@]} ${CKPT_ARGS[@]}\n```\n\n---\n\n## Workflow 1: Standard GRPO Training\n\nUse this workflow for training reasoning models with group-relative advantages.\n\n### Prerequisites Checklist\n- [ ] Docker environment or Megatron-LM + SGLang installed\n- [ ] Model checkpoint (HuggingFace or Megatron format)\n- [ ] Training data in JSONL format\n\n### Step 1: Prepare Data\n\n```python\n# data.jsonl format\n{\"prompt\": \"What is 2 + 2?\", \"label\": \"4\"}\n{\"prompt\": \"Solve: 3x = 12\", \"label\": \"x = 4\"}\n```\n\nOr with chat format:\n```python\n{\n    \"prompt\": [\n        {\"role\": \"system\", \"content\": \"You are a math tutor.\"},\n        {\"role\": \"user\", \"content\": \"What is 15 + 27?\"}\n    ],\n    \"label\": \"42\"\n}\n```\n\n### Step 2: Configure Model\n\nChoose a pre-configured model script:\n\n```bash\n# List available models\nls scripts\u002Fmodels\u002F\n# glm4-9B.sh, qwen3-4B.sh, qwen3-30B-A3B.sh, deepseek-v3.sh, llama3-8B.sh, ...\n\n# Source your model\nsource scripts\u002Fmodels\u002Fqwen3-4B.sh\n```\n\n### Step 3: Launch Training\n\n```bash\npython train.py \\\n    --actor-num-nodes 1 \\\n    --actor-num-gpus-per-node 8 \\\n    --rollout-num-gpus 8 \\\n    --advantage-estimator grpo \\\n    --use-kl-loss \\\n    --kl-loss-coef 0.001 \\\n    --prompt-data \u002Fpath\u002Fto\u002Ftrain.jsonl \\\n    --input-key prompt \\\n    --label-key label \\\n    --apply-chat-template \\\n    --rollout-batch-size 32 \\\n    --n-samples-per-prompt 8 \\\n    --global-batch-size 256 \\\n    --num-rollout 3000 \\\n    --save-interval 100 \\\n    --eval-interval 50 \\\n    ${MODEL_ARGS[@]}\n```\n\n### Step 4: Monitor Training\n- [ ] Check TensorBoard: `tensorboard --logdir outputs\u002F`\n- [ ] Verify reward curves are increasing\n- [ ] Monitor GPU utilization across nodes\n\n---\n\n## Workflow 2: Asynchronous Training\n\nUse async mode for higher throughput by overlapping rollout and training.\n\n### When to Use Async\n- Large models with long generation times\n- High GPU idle time in synchronous mode\n- Sufficient memory for buffering\n\n### Launch Async Training\n\n```bash\npython train_async.py \\\n    --actor-num-nodes 1 \\\n    --actor-num-gpus-per-node 8 \\\n    --rollout-num-gpus 8 \\\n    --advantage-estimator grpo \\\n    --async-buffer-size 4 \\\n    --prompt-data \u002Fpath\u002Fto\u002Ftrain.jsonl \\\n    ${MODEL_ARGS[@]}\n```\n\n### Async-Specific Parameters\n\n```bash\n--async-buffer-size 4        # Number of rollouts to buffer\n--update-weights-interval 2  # Sync weights every N rollouts\n```\n\n---\n\n## Workflow 3: Multi-Turn Agentic Training\n\nUse this workflow for training agents with tool use or multi-step reasoning.\n\n### Prerequisites\n- [ ] Custom generate function for multi-turn logic\n- [ ] Tool\u002Fenvironment interface\n\n### Step 1: Define Custom Generate Function\n\n```python\n# custom_generate.py\nasync def custom_generate(args, samples, evaluation=False):\n    \"\"\"Multi-turn generation with tool calling.\"\"\"\n    for sample in samples:\n        conversation = sample.prompt\n\n        for turn in range(args.max_turns):\n            # Generate response\n            response = await generate_single(conversation)\n\n            # Check for tool call\n            tool_call = extract_tool_call(response)\n            if tool_call:\n                tool_result = execute_tool(tool_call)\n                conversation.append({\"role\": \"assistant\", \"content\": response})\n                conversation.append({\"role\": \"tool\", \"content\": tool_result})\n            else:\n                break\n\n        sample.response = response\n        sample.reward = compute_reward(sample)\n\n    return samples\n```\n\n### Step 2: Launch with Custom Function\n\n```bash\npython train.py \\\n    --custom-generate-function-path custom_generate.py \\\n    --max-turns 5 \\\n    --prompt-data \u002Fpath\u002Fto\u002Fagent_data.jsonl \\\n    ${MODEL_ARGS[@]}\n```\n\nSee `examples\u002Fsearch-r1\u002F` for a complete multi-turn search example.\n\n---\n\n## Configuration Reference\n\n### Three Argument Categories\n\nslime uses three types of arguments:\n\n**1. Megatron Arguments** (passed directly):\n```bash\n--tensor-model-parallel-size 2\n--pipeline-model-parallel-size 1\n--num-layers 32\n--hidden-size 4096\n```\n\n**2. SGLang Arguments** (prefixed with `--sglang-`):\n```bash\n--sglang-mem-fraction-static 0.8\n--sglang-context-length 8192\n--sglang-log-level INFO\n```\n\n**3. slime Arguments**:\n```bash\n# Resource allocation\n--actor-num-nodes 1\n--actor-num-gpus-per-node 8\n--rollout-num-gpus 8\n--colocate  # Share GPUs between training\u002Finference\n\n# Data\n--prompt-data \u002Fpath\u002Fto\u002Fdata.jsonl\n--input-key prompt\n--label-key label\n\n# Training loop\n--num-rollout 3000\n--rollout-batch-size 32\n--n-samples-per-prompt 8\n--global-batch-size 256\n\n# Algorithm\n--advantage-estimator grpo  # or: gspo, ppo, reinforce_plus_plus\n--use-kl-loss\n--kl-loss-coef 0.001\n```\n\n### Key Constraints\n\n```\nrollout_batch_size × n_samples_per_prompt = global_batch_size × num_steps_per_rollout\n```\n\nExample: 32 × 8 = 256 × 1\n\n---\n\n## Data Buffer System\n\nslime's data buffer enables flexible data management:\n\n### Basic Data Source\n\n```python\nclass RolloutDataSource:\n    def get_samples(self, num_samples):\n        \"\"\"Fetch prompts from dataset.\"\"\"\n        return self.dataset.sample(num_samples)\n\n    def add_samples(self, samples):\n        \"\"\"Called after generation (no-op by default).\"\"\"\n        pass\n```\n\n### Buffered Data Source (Off-Policy)\n\n```python\nclass RolloutDataSourceWithBuffer(RolloutDataSource):\n    def __init__(self):\n        self.buffer = []\n\n    def add_samples(self, samples):\n        \"\"\"Store generated samples for reuse.\"\"\"\n        self.buffer.extend(samples)\n\n    def buffer_filter(self, args, buffer, num_samples):\n        \"\"\"Custom selection logic (prioritized, stratified, etc.).\"\"\"\n        return select_best(buffer, num_samples)\n```\n\n---\n\n## Common Issues and Solutions\n\n### Issue: SGLang Engine Crash\n\n**Symptoms**: Inference engine dies mid-training\n\n**Solutions**:\n```bash\n# Enable fault tolerance\n--use-fault-tolerance\n\n# Increase memory allocation\n--sglang-mem-fraction-static 0.85\n\n# Reduce batch size\n--rollout-batch-size 16\n```\n\n### Issue: Weight Sync Timeout\n\n**Symptoms**: Training hangs after rollout\n\n**Solutions**:\n```bash\n# Increase sync interval\n--update-weights-interval 5\n\n# Use colocated mode (no network transfer)\n--colocate\n```\n\n### Issue: OOM During Training\n\n**Symptoms**: CUDA OOM in backward pass\n\n**Solutions**:\n```bash\n# Enable gradient checkpointing\n--recompute-activations\n\n# Reduce micro-batch size\n--micro-batch-size 1\n\n# Enable sequence parallelism\n--sequence-parallel\n```\n\n### Issue: Slow Data Loading\n\n**Symptoms**: GPU idle during data fetch\n\n**Solutions**:\n```bash\n# Increase data workers\n--num-data-workers 4\n\n# Use streaming dataset\n--streaming-data\n```\n\n---\n\n## Supported Models\n\n| Model Family | Configurations |\n|--------------|----------------|\n| GLM | GLM-4.5, GLM-4.6, GLM-4.7, GLM-Z1-9B |\n| Qwen | Qwen3 (4B, 8B, 30B-A3B), Qwen3-MoE, Qwen2.5 |\n| DeepSeek | V3, V3.1, R1 |\n| Llama | Llama 3 (8B, 70B) |\n| Others | Kimi K2, Moonlight-16B |\n\nEach model has pre-configured scripts in `scripts\u002Fmodels\u002F`.\n\n---\n\n## Advanced Topics\n\n### Co-location Mode\n\nShare GPUs between training and inference to reduce memory:\n\n```bash\npython train.py \\\n    --colocate \\\n    --actor-num-gpus-per-node 8 \\\n    --sglang-mem-fraction-static 0.4 \\\n    ${MODEL_ARGS[@]}\n```\n\n### Custom Reward Model\n\n```python\n# custom_rm.py\nclass CustomRewardModel:\n    def __init__(self, model_path):\n        self.model = load_model(model_path)\n\n    def compute_reward(self, prompts, responses):\n        inputs = self.tokenize(prompts, responses)\n        scores = self.model(inputs)\n        return scores.tolist()\n```\n\n```bash\n--custom-rm-path custom_rm.py\n```\n\n### Evaluation Multi-Task\n\n```bash\n--eval-prompt-data aime \u002Fpath\u002Fto\u002Faime.jsonl \\\n--eval-prompt-data gsm8k \u002Fpath\u002Fto\u002Fgsm8k.jsonl \\\n--n-samples-per-eval-prompt 16\n```\n\n---\n\n## Resources\n\n- **Documentation**: https:\u002F\u002Fthudm.github.io\u002Fslime\u002F\n- **GitHub**: https:\u002F\u002Fgithub.com\u002FTHUDM\u002Fslime\n- **Blog**: https:\u002F\u002Flmsys.org\u002Fblog\u002F2025-07-09-slime\u002F\n- **Examples**: See `examples\u002F` directory for 14+ worked examples\n\n## Agent operating procedure\n\n1. **Check the environment.** Check GPU type, memory and driver\u002FCUDA versions (`nvidia-smi`), framework versions, and dataset location and size.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Do a smoke run: tiny model or subset, few steps, and confirm loss decreases and checkpoints save.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Track metrics on held-out data, compare against a baseline, and record seeds, configs and hardware.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| CUDA out-of-memory | Reduce batch size, enable gradient accumulation\u002Fcheckpointing or mixed precision, or shard the model. |\n| Loss is NaN or diverges | Lower the learning rate, check data for invalid values, and enable gradient clipping. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Never claim training results without logs; estimate compute cost before launching large jobs.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `verl-rl-training`: Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL).\n- `miles-rl-training`: Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime.\n- `nanogpt`: Provides nanoGPT, Karpathy's minimal PyTorch GPT implementation (model.py and train.py), with workflows for training character-level Shakes…\n",{"name":5,"license":15,"metadata":44,"description":7},{"tags":45,"version":46,"category":47,"maintainer":48,"dependencies":49},"Reinforcement Learning, Megatron-LM, SGLang, GRPO, Post-Training, GLM","1.0.0","ml-training","Kalaris Labs","sglang-router>=0.2.3, ray, torch>=2.0.0, transformers>=4.40.0","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fkal-slime-rl-training","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6","https:\u002F\u002Fdisha6.6.thenitishkr.in\u002F","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh","www.thenitishkr","thenitishkr | AI • Cyber-security • Research\r\n","2026-11-08 03:33:25",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill slime-rl-training",{"tool":65,"command":66},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill slime-rl-training",{"tool":68,"command":69},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill slime-rl-training","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-slime-rl-training\u002FSKILL.md",true,[73,79],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fapi-reference.md","REFERENCE","参考文档",11907,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-slime-rl-training\u002Freferences\u002Fapi-reference.md",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Ftroubleshooting.md",7221,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-slime-rl-training\u002Freferences\u002Ftroubleshooting.md",[84,115,139,166,191,214],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":95,"publishedAt":39},"01M6QRD07D4TGNDK6VJ4EHF8BV","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-full\u002FSKILL.md",[90],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,37,112,113,114],"youtube full","youtube","full","transcript","search","monitoring","data","Video","Audio","list","files","do","get","age","trigger","URL","browsing","request","youtube transcripts",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":39},"01M6QRCJ3112VYPA97YG7KGMC2","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[122,123,124,125,100,126,127,128,129,130,131,132,133,134,27,135,136,137,138,37],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","write","strategy","platform","grow","posting","competitive",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":148,"publishedAt":39},"01M6QRBN3EHQNJY42RERP7A149","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[145],{"categoryNo":146,"categoryName":147,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000023","Skill与智能体开发",[149,133,150,151,152,153,154,155,27,156,157,50,158,159,160,161,162,163,164,165],"write a skill","github","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":39},"01M6QRB6G8P33PNGAF9Y69EJ9T","wrap-up","Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained .\u002Fmy-agent\u002Fagent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[173,174,175,176,177,178,179,180,181,27,182,107,183,184,185,186,187,188,189,190],"wrap up","up","wrap","gemini","deployment","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":198,"publishedAt":39},"01M6QRA5AYC1RBFZ39GTWGS3N8","workflow-builder","Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-builder\u002FSKILL.md",[197],{"categoryNo":146,"categoryName":147,"taxonomyType":93,"taxonomyTypeDesc":94},[199,200,201,202,33,151,178,203,204,205,206,207,133,208,106,209,210,211,212,213],"workflow","workflow builder","builder","design","code","orchestrate","pipeline","loop","multi-agent","context","across","fresh","scripts","judge","claude code workflow",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":220,"publishedAt":39},"01M6QR7QMCZESKQA0ERW1E657M","weekly-review","Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"\u002Fcs:weekly-review\". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[221,222,223,224,225,226,227,228,229,206,230,231,232,233,234,235,108,236,237,190],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","open","team","projects","project-management","scanner","conversation","back","project","sprint","cadence"]