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(model): fix bugs of batch generation & support min_new_tokens for inference #313

Merged
merged 3 commits into from
Sep 4, 2024

Conversation

x54-729
Copy link
Contributor

@x54-729 x54-729 commented Sep 3, 2024

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Please describe the motivation of this PR and the goal you want to achieve through this PR.

Modification

  1. 修复 batch generation 时 dones 张量在 logic or 操作后形状变为 (batch_size, batch_size) 的 bug
  2. 修复 batch generation 计算 rope 前 q k padding 位置移动错误的 bug
  3. 修复 batch generation 计算 rope 时 q k 没有正确 pack 的 bug
  4. 更新 min_new_tokens 功能

BC-breaking (Optional)

Does the modification introduce changes that break the backward compatibility of the downstream repositories?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here and update the documentation.

Checklist

Before PR:

  • Pre-commit or other linting tools are used to fix the potential lint issues.
  • Bug fixes are fully covered by unit tests, the case that causes the bug should be added in the unit tests.
  • The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
  • The documentation has been modified accordingly, like docstring or example tutorials.

After PR:

  • If the modification has potential influence on downstream or other related projects, this PR should be tested with those projects.
  • CLA has been signed and all committers have signed the CLA in this PR.

@x54-729 x54-729 changed the title fix(model): fix bugs of batch generation fix(model): fix bugs of batch generation & support mix_new_tokens for inference Sep 3, 2024
@x54-729 x54-729 changed the title fix(model): fix bugs of batch generation & support mix_new_tokens for inference fix(model): fix bugs of batch generation & support min_new_tokens for inference Sep 3, 2024
internlm/apis/inference.py Outdated Show resolved Hide resolved
internlm/model/modules/mha.py Show resolved Hide resolved
@gaoyang07 gaoyang07 self-assigned this Sep 3, 2024
@gaoyang07 gaoyang07 added the bug Something isn't working label Sep 3, 2024
@gaoyang07 gaoyang07 merged commit 8ab2aff into InternLM:develop Sep 4, 2024
19 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants