Skip to content

[pick][llm] Add a generic text only LLM runner #11441

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 8 commits into from
Jun 6, 2025
Merged

[pick][llm] Add a generic text only LLM runner #11441

merged 8 commits into from
Jun 6, 2025

Conversation

@larryliu0820
Copy link
Contributor

@larryliu0820 larryliu0820 commented Jun 6, 2025

Picking from #11342

Introducing text_llm_runner. This can be used to run all text only decoder only LLM models supported by ExecuTorch.

  • Metadata is being read out from the .pte file and being used to construct the runner object.
  • examples/models/llama/runner.h[.cpp] only contains a simple wrapper around text_llm_runner.h[.cpp].

In next PRs I will move examples/models/phi-3-mini/runner to use the generic runner.

Will look into QNN and MediaTek runners as well.

Differential Revision: D75910889

larryliu0820 and others added 8 commits June 4, 2025 09:45
@larryliu0820
Update base for Update on "[llm] Add a generic text only LLM runner"
0845100 
Introducing `text_llm_runner`. This can be used to run all text only decoder only LLM models supported by ExecuTorch.

* Metadata is being read out from the .pte file and being used to construct the runner object.
* examples/models/llama/runner.h[.cpp] only contains a simple wrapper around `text_llm_runner.h[.cpp]`.


In next PRs I will move examples/models/phi-3-mini/runner to use the generic runner.

Will look into QNN and MediaTek runners as well.

Differential Revision: [D75910889](https://our.internmc.facebook.com/intern/diff/D75910889/)

[ghstack-poisoned]
@larryliu0820
Update base for Update on "[llm] Add a generic text only LLM runner"
d0e7faa 
Introducing `text_llm_runner`. This can be used to run all text only decoder only LLM models supported by ExecuTorch.

* Metadata is being read out from the .pte file and being used to construct the runner object.
* examples/models/llama/runner.h[.cpp] only contains a simple wrapper around `text_llm_runner.h[.cpp]`.


In next PRs I will move examples/models/phi-3-mini/runner to use the generic runner.

Will look into QNN and MediaTek runners as well.

Differential Revision: [D75910889](https://our.internmc.facebook.com/intern/diff/D75910889/)

[ghstack-poisoned]
@larryliu0820
Update base for Update on "[llm] Add a generic text only LLM runner"
a05c2e9 
Introducing `text_llm_runner`. This can be used to run all text only decoder only LLM models supported by ExecuTorch.

* Metadata is being read out from the .pte file and being used to construct the runner object.
* examples/models/llama/runner.h[.cpp] only contains a simple wrapper around `text_llm_runner.h[.cpp]`.


In next PRs I will move examples/models/phi-3-mini/runner to use the generic runner.

Will look into QNN and MediaTek runners as well.

Differential Revision: [D75910889](https://our.internmc.facebook.com/intern/diff/D75910889/)

[ghstack-poisoned]
@larryliu0820
Update base for Update on "[llm] Add a generic text only LLM runner"
8a69060 
Introducing `text_llm_runner`. This can be used to run all text only decoder only LLM models supported by ExecuTorch.

* Metadata is being read out from the .pte file and being used to construct the runner object.
* examples/models/llama/runner.h[.cpp] only contains a simple wrapper around `text_llm_runner.h[.cpp]`.


In next PRs I will move examples/models/phi-3-mini/runner to use the generic runner.

Will look into QNN and MediaTek runners as well.

Differential Revision: [D75910889](https://our.internmc.facebook.com/intern/diff/D75910889/)

[ghstack-poisoned]
@larryliu0820
Update base for Update on "[llm] Add a generic text only LLM runner"
7607d7d 
Introducing `text_llm_runner`. This can be used to run all text only decoder only LLM models supported by ExecuTorch.

* Metadata is being read out from the .pte file and being used to construct the runner object.
* examples/models/llama/runner.h[.cpp] only contains a simple wrapper around `text_llm_runner.h[.cpp]`.


In next PRs I will move examples/models/phi-3-mini/runner to use the generic runner.

Will look into QNN and MediaTek runners as well.

Differential Revision: [D75910889](https://our.internmc.facebook.com/intern/diff/D75910889/)

[ghstack-poisoned]
@larryliu0820
Update base for Update on "[llm] Add a generic text only LLM runner"
61182e6 
Introducing `text_llm_runner`. This can be used to run all text only decoder only LLM models supported by ExecuTorch.

* Metadata is being read out from the .pte file and being used to construct the runner object.
* examples/models/llama/runner.h[.cpp] only contains a simple wrapper around `text_llm_runner.h[.cpp]`.


In next PRs I will move examples/models/phi-3-mini/runner to use the generic runner.

Will look into QNN and MediaTek runners as well.

Differential Revision: [D75910889](https://our.internmc.facebook.com/intern/diff/D75910889/)

[ghstack-poisoned]
@larryliu0820
Update base for Update on "[llm] Add a generic text only LLM runner"
009282a 
Introducing `text_llm_runner`. This can be used to run all text only decoder only LLM models supported by ExecuTorch.

* Metadata is being read out from the .pte file and being used to construct the runner object.
* examples/models/llama/runner.h[.cpp] only contains a simple wrapper around `text_llm_runner.h[.cpp]`.


In next PRs I will move examples/models/phi-3-mini/runner to use the generic runner.

Will look into QNN and MediaTek runners as well.

Differential Revision: [D75910889](https://our.internmc.facebook.com/intern/diff/D75910889/)

[ghstack-poisoned]
@larryliu0820
[llm] Add a generic text only LLM runner
e3c6543 
Differential Revision: D75910889

Pull Request resolved: #11342
@pytorch-bot
Copy link

pytorch-bot bot commented Jun 6, 2025 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11441

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

⏳ 1 Pending, 4 Unrelated Failures

As of commit e3c6543 with merge base b2c02fe (image):

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

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

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Jun 6, 2025
@larryliu0820 larryliu0820 added the release notes: llm Changes to llm utilities label Jun 6, 2025
@larryliu0820 larryliu0820 merged commit 27cb43d into main Jun 6, 2025
265 of 288 checks passed
@larryliu0820 larryliu0820 deleted the gh/larryliu0820/65/base branch June 6, 2025 18:36
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@lucylq lucylq lucylq approved these changes

@jathu jathu Awaiting requested review from jathu

@kirklandsign kirklandsign Awaiting requested review from kirklandsign kirklandsign is a code owner

@jackzhxng jackzhxng Awaiting requested review from jackzhxng jackzhxng is a code owner

@iseeyuan iseeyuan Awaiting requested review from iseeyuan

@swolchok swolchok Awaiting requested review from swolchok

@shoumikhin shoumikhin Awaiting requested review from shoumikhin shoumikhin is a code owner

Assignees

No one assigned

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. release notes: llm Changes to llm utilities

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@larryliu0820 @lucylq @facebook-github-bot