Skip to content
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.

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

Fix llama_triton_example #1414

Merged
merged 1 commit into from
Apr 9, 2024
Merged

Fix llama_triton_example #1414

merged 1 commit into from
Apr 9, 2024

Conversation

AllentDan
Copy link
Collaborator

if (name == "bad_words_list" || name == "stop_words_list") {
for (int i = 0; i < batch_size; ++i) {
if (state_->requests[i]->inputs[rank_].isExist(name)) {
Tensor& src = state_->requests[i]->inputs[rank_].at(name);
FT_CHECK(src.shape.size() == 3 && src.shape[1] == 2 && src.shape[2] <= kMaxStopBadWordsLen);
max_list_length = std::max(max_list_length, (int)src.shape[2]);
}
}

@zhyncs
Copy link
Contributor

zhyncs commented Apr 9, 2024

@AllentDan May you give a request example

@AllentDan
Copy link
Collaborator Author

AllentDan commented Apr 9, 2024

Just the example failed. May run build/bin/llama_triton_example examples/cpp/llama/llama_config.ini examples/cpp/llama/start_ids.csv, it will raise an error.

@zhyncs
Copy link
Contributor

zhyncs commented Apr 9, 2024

Just the example failed. May run build/bin/llama_triton_example examples/cpp/llama/llama_config.ini examples/cpp/llama/start_ids.csv, it will raise an error.

make sense #1246

@zhyncs
Copy link
Contributor

zhyncs commented Apr 9, 2024

LGTM

@lvhan028 lvhan028 merged commit b5b2b8b into InternLM:main Apr 9, 2024
7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

4 participants