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.
npxskills add orchestra-research/ai-research-skills--skill slime-rl-trainingLoading…
slime 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.
Choose slime when you need:
Consider alternatives when:
┌─────────────────────────────────────────────────────────┐
│ Data Buffer │
│ - Prompt initialization and management │
│ - Custom data generation and filtering │
│ - Rollout sample storage │
└─────────────┬───────────────────────────┬───────────────┘
│ │
┌─────────────▼───────────┐ ┌─────────────▼───────────────┐
│ Training (Megatron-LM) │ │ Rollout (SGLang + Router) │
│ - Actor model training │ │ - Response generation │
│ - Critic (optional) │ │ - Reward/verifier output │
│ - Weight sync to rollout│ │ - Multi-turn support │
└─────────────────────────┘ └─────────────────────────────┘
# Recommended: Docker
docker pull slimerl/slime:latest
docker run --rm --gpus all --ipc=host --shm-size=16g \
-it slimerl/slime:latest /bin/bash
# Inside container
cd /root/slime && pip install -e . --no-deps
git clone https://github.com/THUDM/slime.git
cd slime
pip install -r requirements.txt
pip install -e .
# Source model configuration
source scripts/models/qwen3-4B.sh
# Launch training
python train.py \
--actor-num-nodes 1 \
--actor-num-gpus-per-node 4 \
--rollout-num-gpus 4 \
--advantage-estimator grpo \
--use-kl-loss --kl-loss-coef 0.001 \
--rollout-batch-size 32 \
--n-samples-per-prompt 8 \
--global-batch-size 256 \
--num-rollout 3000 \
--prompt-data /path/to/data.jsonl \
${MODEL_ARGS[@]} ${CKPT_ARGS[@]}
Use this workflow for training reasoning models with group-relative advantages.
# data.jsonl format
{"prompt": "What is 2 + 2?", "label": "4"}
{"prompt": "Solve: 3x = 12", "label": "x = 4"}
Or with chat format:
{
"prompt": [
{"role": "system", "content": "You are a math tutor."},
{"role": "user", "content": "What is 15 + 27?"}
],
"label": "42"
}
Choose a pre-configured model script:
# List available models
ls scripts/models/
# glm4-9B.sh, qwen3-4B.sh, qwen3-30B-A3B.sh, deepseek-v3.sh, llama3-8B.sh, ...
# Source your model
source scripts/models/qwen3-4B.sh
python train.py \
--actor-num-nodes 1 \
--actor-num-gpus-per-node 8 \
--rollout-num-gpus 8 \
--advantage-estimator grpo \
--use-kl-loss \
--kl-loss-coef 0.001 \
--prompt-data /path/to/train.jsonl \
--input-key prompt \
--label-key label \
--apply-chat-template \
--rollout-batch-size 32 \
--n-samples-per-prompt 8 \
--global-batch-size 256 \
--num-rollout 3000 \
--save-interval 100 \
--eval-interval 50 \
${MODEL_ARGS[@]}
tensorboard --logdir outputs/Use async mode for higher throughput by overlapping rollout and training.
python train_async.py \
--actor-num-nodes 1 \
--actor-num-gpus-per-node 8 \
--rollout-num-gpus 8 \
--advantage-estimator grpo \
--async-buffer-size 4 \
--prompt-data /path/to/train.jsonl \
${MODEL_ARGS[@]}
--async-buffer-size 4 # Number of rollouts to buffer
--update-weights-interval 2 # Sync weights every N rollouts
Use this workflow for training agents with tool use or multi-step reasoning.
# custom_generate.py
async def custom_generate(args, samples, evaluation=False):
"""Multi-turn generation with tool calling."""
for sample in samples:
conversation = sample.prompt
for turn in range(args.max_turns):
# Generate response
response = await generate_single(conversation)
# Check for tool call
tool_call = extract_tool_call(response)
if tool_call:
tool_result = execute_tool(tool_call)
conversation.append({"role": "assistant", "content": response})
conversation.append({"role": "tool", "content": tool_result})
else:
break
sample.response = response
sample.reward = compute_reward(sample)
return samples
python train.py \
--custom-generate-function-path custom_generate.py \
--max-turns 5 \
--prompt-data /path/to/agent_data.jsonl \
${MODEL_ARGS[@]}
See examples/search-r1/ for a complete multi-turn search example.
slime uses three types of arguments:
1. Megatron Arguments (passed directly):
--tensor-model-parallel-size 2
--pipeline-model-parallel-size 1
--num-layers 32
--hidden-size 4096
2. SGLang Arguments (prefixed with --sglang-):
--sglang-mem-fraction-static 0.8
--sglang-context-length 8192
--sglang-log-level INFO
3. slime Arguments:
# Resource allocation
--actor-num-nodes 1
--actor-num-gpus-per-node 8
--rollout-num-gpus 8
--colocate # Share GPUs between training/inference
# Data
--prompt-data /path/to/data.jsonl
--input-key prompt
--label-key label
# Training loop
--num-rollout 3000
--rollout-batch-size 32
--n-samples-per-prompt 8
--global-batch-size 256
# Algorithm
--advantage-estimator grpo # or: gspo, ppo, reinforce_plus_plus
--use-kl-loss
--kl-loss-coef 0.001
rollout_batch_size × n_samples_per_prompt = global_batch_size × num_steps_per_rollout
Example: 32 × 8 = 256 × 1
slime's data buffer enables flexible data management:
class RolloutDataSource:
def get_samples(self, num_samples):
"""Fetch prompts from dataset."""
return self.dataset.sample(num_samples)
def add_samples(self, samples):
"""Called after generation (no-op by default)."""
pass
class RolloutDataSourceWithBuffer(RolloutDataSource):
def __init__(self):
self.buffer = []
def add_samples(self, samples):
"""Store generated samples for reuse."""
self.buffer.extend(samples)
def buffer_filter(self, args, buffer, num_samples):
"""Custom selection logic (prioritized, stratified, etc.)."""
return select_best(buffer, num_samples)
Symptoms: Inference engine dies mid-training
Solutions:
# Enable fault tolerance
--use-fault-tolerance
# Increase memory allocation
--sglang-mem-fraction-static 0.85
# Reduce batch size
--rollout-batch-size 16
Symptoms: Training hangs after rollout
Solutions:
# Increase sync interval
--update-weights-interval 5
# Use colocated mode (no network transfer)
--colocate
Symptoms: CUDA OOM in backward pass
Solutions:
# Enable gradient checkpointing
--recompute-activations
# Reduce micro-batch size
--micro-batch-size 1
# Enable sequence parallelism
--sequence-parallel
Symptoms: GPU idle during data fetch
Solutions:
# Increase data workers
--num-data-workers 4
# Use streaming dataset
--streaming-data
| Model Family | Configurations |
|---|---|
| GLM | GLM-4.5, GLM-4.6, GLM-4.7, GLM-Z1-9B |
| Qwen | Qwen3 (4B, 8B, 30B-A3B), Qwen3-MoE, Qwen2.5 |
| DeepSeek | V3, V3.1, R1 |
| Llama | Llama 3 (8B, 70B) |
| Others | Kimi K2, Moonlight-16B |
Each model has pre-configured scripts in scripts/models/.
Share GPUs between training and inference to reduce memory:
python train.py \
--colocate \
--actor-num-gpus-per-node 8 \
--sglang-mem-fraction-static 0.4 \
${MODEL_ARGS[@]}
# custom_rm.py
class CustomRewardModel:
def __init__(self, model_path):
self.model = load_model(model_path)
def compute_reward(self, prompts, responses):
inputs = self.tokenize(prompts, responses)
scores = self.model(inputs)
return scores.tolist()
--custom-rm-path custom_rm.py
--eval-prompt-data aime /path/to/aime.jsonl \
--eval-prompt-data gsm8k /path/to/gsm8k.jsonl \
--n-samples-per-eval-prompt 16
examples/ directory for 14+ worked examples
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).