Add missing runner_lib dep to main_static (#19210)#19210
Merged
rascani merged 1 commit intopytorch:mainfrom May 4, 2026
Merged
Add missing runner_lib dep to main_static (#19210)#19210rascani merged 1 commit intopytorch:mainfrom
rascani merged 1 commit intopytorch:mainfrom
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19210
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Contributor
|
@rascani has exported this pull request. If you are a Meta employee, you can view the originating Diff in D103028501. |
meta-cla
Bot
added
the
CLA Signed
This PR needs a
|
lucylq
approved these changes
Apr 29, 2026
meta-codesync
Bot
changed the title
rascani
added a commit
to rascani/executorch
that referenced
this pull request
May 4, 2026
Summary: D82497138 added new transitive includes (`constants.h`, `multimodal_prefiller.h`, `extension/tensor/tensor.h`) into `executorch/extension/llm/runner/util.h`. The llava `main.cpp` already includes `multimodal_runner.h`, `multimodal_input.h`, and `image.h`, and calls `create_multimodal_runner` and `load_tokenizer` from `llm_runner_helper`, but the `main` (and auto-generated `main_static`) target only declared `print_evalue` and `threadpool` deps. After D82497138 the compile fails with `Action failed: ... (cxx_compile main.cpp) Remote command returned non-zero exit code 1` because the `runner_lib` headers cannot be found. Add `//executorch/extension/llm/runner:runner_lib` (which transitively re-exports `multimodal_runner_lib` and provides `llm_runner_helper`) to the deps of the `main` cxx_binary so the static variant resolves all required headers and symbols. Also wire the existing `seq_len` flag into `GenerationConfig::seq_len` (it was previously read from gflags but never used, which trips `-Werror=unused-variable` once the headers compile). Reviewed By: psiddh Differential Revision: D103028501
Summary: D82497138 added new transitive includes (`constants.h`, `multimodal_prefiller.h`, `extension/tensor/tensor.h`) into `executorch/extension/llm/runner/util.h`. The llava `main.cpp` already includes `multimodal_runner.h`, `multimodal_input.h`, and `image.h`, and calls `create_multimodal_runner` and `load_tokenizer` from `llm_runner_helper`, but the `main` (and auto-generated `main_static`) target only declared `print_evalue` and `threadpool` deps. After D82497138 the compile fails with `Action failed: ... (cxx_compile main.cpp) Remote command returned non-zero exit code 1` because the `runner_lib` headers cannot be found. Add `//executorch/extension/llm/runner:runner_lib` (which transitively re-exports `multimodal_runner_lib` and provides `llm_runner_helper`) to the deps of the `main` cxx_binary so the static variant resolves all required headers and symbols. Also wire the existing `seq_len` flag into `GenerationConfig::seq_len` (it was previously read from gflags but never used, which trips `-Werror=unused-variable` once the headers compile). Reviewed By: psiddh Differential Revision: D103028501
Contributor
|
Thank you! I was about to do the same fix :) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary:
D82497138 added new transitive includes (
constants.h,multimodal_prefiller.h,extension/tensor/tensor.h) intoexecutorch/extension/llm/runner/util.h. The llavamain.cppalready includesmultimodal_runner.h,multimodal_input.h, andimage.h, and callscreate_multimodal_runnerandload_tokenizerfromllm_runner_helper, but themain(and auto-generatedmain_static) target only declaredprint_evalueandthreadpooldeps. After D82497138 the compile fails withAction failed: ... (cxx_compile main.cpp) Remote command returned non-zero exit code 1because therunner_libheaders cannot be found.Add
//executorch/extension/llm/runner:runner_lib(which transitively re-exportsmultimodal_runner_liband providesllm_runner_helper) to the deps of themaincxx_binary so the static variant resolves all required headers and symbols. Also wire the existingseq_lenflag intoGenerationConfig::seq_len(it was previously read from gflags but never used, which trips-Werror=unused-variableonce the headers compile).Reviewed By: psiddh
Differential Revision: D103028501