Qualcomm AI Engine Direct - Enable Lookahead Decoding

[shewu-quic]

Summary:

• Add new eval_mode: lookahead
• Add three arguments: ngram, window, gcap
• Add lhd_token_generator

Command

python3 examples/qualcomm/oss_scripts/llama/llama.py -b build-android --checkpoint stories110M.pt --params params.json --tokenizer_model tokenizer.model --prompt "Once" --temperature 0 --tokenizer_bin tokenizer.bin --llama_model stories110m --model_mode lookahead --ptq 16a4w -m SM8650 -H ${host} -s ${device}  -a ${artifacts} --max_seq_len 4096 --kv_updater smart_mask  --prefill_ar_len 64 --ngram 3 --window 2 --gcap 2

Test Results

QNN SDK: 2.28
Device: SM8650
max_seq_len: 4096

Performance Improvement under different AR-N and different W/G/N

Llama 3.2 3B

Llama 3.2 1B

Story Llama 110M

Performance Improvement under different prompt

Reference

• https://lmsys.org/blog/2023-11-21-lookahead-decoding/
• https://github.com/hao-ai-lab/LookaheadDecoding/tree/main/lade
• https://github.com/ggml-org/llama.cpp/blob/master/examples/lookahead/lookahead.cpp

cc: @haowhsu-quic

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11437

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❌ 1 New Failure

As of commit 6bd4645 with merge base 56392aa ():

NEW FAILURE - The following job has failed:

• Lint / lintrunner / linux-job (gh)
  RuntimeError: Command docker exec -t e368a39b51fa7fd6f04d143c70d9df48f9a096e6c9c989f1abce042e72715bc5 /exec failed with exit code 127

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

[cccclai]

Hey can you add a read me to explain how this specific lookahead decoding work? Also, does 0/0/0 mean no lookahead decoding?

[cccclai]

It looks great!

[shewu-quic]

Hey can you add a read me to explain how this specific lookahead decoding work? Also, does 0/0/0 mean no lookahead decoding?

Sure. Let me work on it.
Yes, 0/0/0 means AR-N decoding without lookahead.
I manually change ar_len of decoding model in hybrid mode.

executorch/examples/qualcomm/oss_scripts/llama/llama.py

Line 519 in 56392aa

ar_len=1,

[facebook-github-bot]

@cccclai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.