ChessLM_Qwen3_Trainium

ChessLM Qwen3 - Neuron Traced for AWS Trainium/Inferentia (Continuous Batching)

This is a Neuron-traced version of karanps/ChessLM_Qwen3 optimized for AWS Trainium (trn1) and Inferentia (inf2) instances using vLLM with continuous batching enabled.

Model Details

• Base Model: Qwen3-8B fine-tuned for chess
• Compilation: optimum-neuron[vllm]==0.3.0
• Compiler Version: neuronxcc 2.21.33363.0
• Target Hardware: AWS Trainium (trn1) / Inferentia (inf2)
• Precision: BF16
• Tensor Parallelism: 2 cores
• Batch Size: 4 (continuous batching enabled)
• Max Sequence Length: 2048
• On-Device Sampling: Disabled (due to runtime limitation with TP=2)

Requirements

pip install optimum-neuron[vllm]==0.3.0
pip install neuronx-distributed --extra-index-url=https://pip.repos.neuron.amazonaws.com

Usage

Loading the Model

from optimum.neuron import NeuronModelForCausalLM
from transformers import AutoTokenizer

# Load the traced model
model = NeuronModelForCausalLM.from_pretrained("kunhunjon/ChessLM_Qwen3_Trainium")
tokenizer = AutoTokenizer.from_pretrained("kunhunjon/ChessLM_Qwen3_Trainium")

# Run inference
prompt = "e2e4"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)

Hardware Requirements

• AWS Trainium (trn1.32xlarge, trn1.2xlarge) or Inferentia (inf2) instances
• At least 2 Neuron cores (as configured during tracing)
• Minimum 32GB RAM recommended

Compilation Details

This model was traced with the following parameters:

• batch_size=4
• sequence_length=2048
• num_cores=2
• auto_cast_type="bf16"
• continuous_batching=True
• vLLM-compatible compilation

Continuous Batching

This model is compiled with continuous batching enabled, which allows vLLM to:

• Process multiple requests simultaneously with dynamic batch sizes up to 4
• Optimize throughput by batching requests with different sequence lengths
• Reduce latency for concurrent inference workloads

Note: On-device sampling is disabled due to a known Neuron runtime limitation when using tensor parallelism with 2 cores. Sampling is handled on the host instead.

Compilation Metrics

• Total compilation time: ~8.1 minutes
• Token generation model: 219 seconds
• Context encoding model: 165 seconds
• Model size: 17GB

License

This model inherits the license from the base model karanps/ChessLM_Qwen3.

Citation

If you use this model, please cite the original ChessLM model and AWS Neuron tools.