Slime

# 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[@]}

--tensor-model-parallel-size 2
--pipeline-model-parallel-size 1
--num-layers 32
--hidden-size 4096

--sglang-mem-fraction-static 0.8
--sglang-context-length 8192
--sglang-log-level INFO

# 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

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)

# Enable fault tolerance
--use-fault-tolerance

# Increase memory allocation
--sglang-mem-fraction-static 0.85

# Reduce batch size
--rollout-batch-size 16

# Increase sync interval
--update-weights-interval 5

# Use colocated mode (no network transfer)
--colocate

# Enable gradient checkpointing
--recompute-activations

# Reduce micro-batch size
--micro-batch-size 1

# Enable sequence parallelism
--sequence-parallel

# Increase data workers
--num-data-workers 4

# Use streaming dataset
--streaming-data

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