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

Set&Get llm internal tokenizer instead of the TokenizerGroup #2741

Merged
merged 1 commit into from
Feb 4, 2024
Merged

Set&Get llm internal tokenizer instead of the TokenizerGroup #2741

merged 1 commit into from
Feb 4, 2024

Conversation

dancingpipi
Copy link
Contributor

@dancingpipi dancingpipi commented Feb 4, 2024 •
edited
Loading

Since LLMEngine uses TokenizerGroup, the get_tokenizer and set_tokenizer methods in LLM need to be adjusted so that they operate on the original tokenizer in LLMEngine.
@WoosukKwon

@dancingpipi dancingpipi changed the title set&get llm internal tokenizer instead of the TokenizerGroup [BUG] Set&Get llm internal tokenizer instead of the TokenizerGroup Feb 4, 2024
@dancingpipi dancingpipi changed the title [BUG] Set&Get llm internal tokenizer instead of the TokenizerGroup Set&Get llm internal tokenizer instead of the TokenizerGroup Feb 4, 2024
zhuohan123
zhuohan123 approved these changes Feb 4, 2024
View reviewed changes
Copy link
Member

@zhuohan123 zhuohan123 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM! Thanks for the fix!

@zhuohan123 zhuohan123 merged commit 51cd22c into vllm-project:main Feb 4, 2024
17 checks passed
@zhuohan123 zhuohan123 mentioned this pull request Feb 4, 2024
Closed
hongxiayang pushed a commit to hongxiayang/vllm that referenced this pull request Feb 13, 2024
@dancingpipi
set&get llm internal tokenizer instead of the TokenizerGroup (vllm-pr…
c7bf3af 
…oject#2741)

Co-authored-by: shujunhua1 <shujunhua1@jd.com>
alexm-redhat pushed a commit to neuralmagic/nm-vllm that referenced this pull request Feb 13, 2024
@dancingpipi @alexm-redhat
set&get llm internal tokenizer instead of the TokenizerGroup (vllm-pr…
22fa755 
…oject#2741)

Co-authored-by: shujunhua1 <shujunhua1@jd.com>
xjpang pushed a commit to xjpang/vllm that referenced this pull request Feb 20, 2024
@dancingpipi
set&get llm internal tokenizer instead of the TokenizerGroup (vllm-pr…
13afc52 
…oject#2741)

Co-authored-by: shujunhua1 <shujunhua1@jd.com>
xjpang pushed a commit to xjpang/vllm that referenced this pull request Feb 22, 2024
@dancingpipi
set&get llm internal tokenizer instead of the TokenizerGroup (vllm-pr…
6bd9ebd 
…oject#2741)

Co-authored-by: shujunhua1 <shujunhua1@jd.com>
@andy-neuma andy-neuma mentioned this pull request Feb 23, 2024
Closed
xjpang pushed a commit to xjpang/vllm that referenced this pull request Mar 4, 2024
@dancingpipi
set&get llm internal tokenizer instead of the TokenizerGroup (vllm-pr…
93bdc0b 
…oject#2741)

Co-authored-by: shujunhua1 <shujunhua1@jd.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@zhuohan123 zhuohan123 zhuohan123 approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@dancingpipi @zhuohan123