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.

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

[Tracking] Sampler optimization #199

Open
1 of 2 tasks
masahi opened this issue Feb 8, 2024 · 2 comments
Open
1 of 2 tasks

[Tracking] Sampler optimization #199

masahi opened this issue Feb 8, 2024 · 2 comments

Comments

@masahi
Copy link
Member

masahi commented Feb 8, 2024 •
edited
Loading

Let's collect remaining issues we are aware of related to sampler performance
@masahi
Copy link
Member Author

masahi commented Feb 21, 2024

The first issue seems to have been fixed by @vvchernov #215

@vvchernov
Copy link

Hello @masahi! No, my fix in #215 resolved very strong (more than one order) reduction after #214.
About task 1: 1. we observed reduction ~25-30% after #192 2. It was not resolved, I'm investigating the issue
About task 2: I remember about logprobs, but looks like resolving of task 1 requires sampler refactor and I want to do it first (or somebody will do it)

Lunderberg pushed a commit to Lunderberg/mlc-llm that referenced this issue Feb 27, 2024
@tqchen
API Consistency (octoml#199)
b76d5d3 
This PR makes API to be consistent across iOS and C++ implementation.

- Use ChatModule as the wrapper API.
- Use the same function name across implementations
  modulo style to match language native preference
- Initial round of documentations about these API
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@masahi @vvchernov