CoolFace
Modelpublic

larryliu0820/Qwen3-1.7B-ExecuTorch-XNNPACK

sourceHugging Faceapache-2.0updated 8mo agoView on Hugging Face
0likes18downloads
Model Card

Qwen3-1.7B (ExecuTorch, XNNPACK, fp32)

This folder contains an ExecuTorch .pte export of `Qwen/Qwen3-1.7B` for CPU inference via the XNNPACK backend.

Contents

  • —model.pte: ExecuTorch program
  • —tokenizer.json, vocab.json, merges.txt: tokenizer artifacts
  • —config.json, generation_config.json, tokenizer_config.json: metadata files from the upstream Hugging Face repo

Export details

  • —Task: text-generation
  • —Recipe: xnnpack
  • —Flags: --use_custom_sdpa --use_custom_kv_cache
  • —Weight dtype: float32 (no quantization)

Tooling versions used to generate these artifacts:

  • —ExecuTorch: executorch==1.2.0a0+d265acf (git d265acfb63)
  • —Optimum ExecuTorch: optimum-executorch==0.2.0.dev0 (git 4c62ed77)

Command used:

bash
optimum-cli export executorch \
  --model "Qwen/Qwen3-1.7B" \
  --task "text-generation" \
  --recipe "xnnpack" \
  --use_custom_sdpa \
  --use_custom_kv_cache \
  --output_dir "<output_dir>"

Run with the ExecuTorch Llama runner

Build the runner from the ExecuTorch repo root:

bash
make llama-cpu

Binary: cmake-out/examples/models/llama/llama_main

bash
cmake-out/examples/models/llama/llama_main \
  --model_path "model.pte" \
  --tokenizer_path "tokenizer.json" \
  --prompt "Simply put, the theory of relativity states that" \
  --max_new_tokens 48 \
  --temperature 0