Skip to content

feat: Refactor LLM model zoo and add KV cache support#3527

Merged
peri044 merged 40 commits intomainfrom
kv_cache
Jul 3, 2025
Merged

feat: Refactor LLM model zoo and add KV cache support#3527
peri044 merged 40 commits intomainfrom
kv_cache

Conversation

@peri044
Copy link
Copy Markdown
Collaborator

@peri044 peri044 commented May 20, 2025 •
edited
Loading

Description

This PR redesigns our LLM model compilation, unifies it, fixes output mismatch and performance issues. This PR also implements KV caching using native TensorRT.

Fixes # (issue)

Type of change

  • New feature (non-breaking change which adds functionality)
  • This change requires a documentation update

Checklist:

  • My code follows the style guidelines of this project (You can use the linters)
  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas and hacks
  • I have made corresponding changes to the documentation
  • I have added tests to verify my fix or my feature
  • New and existing unit tests pass locally with my changes
  • I have added the relevant labels to my PR in so that relevant reviewers are notified

@peri044 peri044 added the WIP Work is in progress, pull request should not be merged yet label May 20, 2025
@peri044 peri044 marked this pull request as draft May 20, 2025 23:30
@github-actions github-actions bot added component: lowering Issues re: The lowering / preprocessing passes component: conversion Issues re: Conversion stage component: api [Python] Issues re: Python API component: runtime component: dynamo Issues relating to the `torch.compile` or `torch._dynamo.export` paths labels May 20, 2025
@github-actions github-actions bot requested a review from gs-olive May 20, 2025 23:30
@peri044 peri044 changed the title feat : caching attempts feat: caching attempts May 20, 2025
@peri044 peri044 removed the request for review from gs-olive May 21, 2025 00:40
github-actions[bot]

This comment was marked as spam.

Sign in to view

github-actions[bot]

This comment was marked as outdated.

Sign in to view

github-actions[bot]

This comment was marked as outdated.

Sign in to view

@peri044 peri044 changed the title feat: caching attempts feat: Refactor LLM optimization and add KV cache support Jun 13, 2025
@peri044 peri044 changed the title feat: Refactor LLM optimization and add KV cache support feat: Refactor LLM model zoo and add KV cache support Jun 13, 2025
@github-actions github-actions bot removed the component: lowering Issues re: The lowering / preprocessing passes label Jun 13, 2025
@github-actions github-actions bot added the documentation Improvements or additions to documentation label Jun 13, 2025
narendasan
narendasan reviewed Jun 13, 2025
View reviewed changes
narendasan
narendasan reviewed Jun 13, 2025
View reviewed changes
narendasan
narendasan reviewed Jun 13, 2025
View reviewed changes
narendasan
narendasan reviewed Jun 13, 2025
View reviewed changes
zewenli98
zewenli98 reviewed Jun 14, 2025
View reviewed changes
Copy link
Copy Markdown
Collaborator

@zewenli98 zewenli98 left a comment

Choose a reason for hiding this comment

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

Mostly LGTM. just some questions

zewenli98
zewenli98 reviewed Jun 17, 2025
View reviewed changes
Copy link
Copy Markdown
Collaborator

@zewenli98 zewenli98 left a comment

Choose a reason for hiding this comment

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

same questions above

narendasan
narendasan approved these changes Jun 17, 2025
View reviewed changes
Copy link
Copy Markdown
Collaborator

@narendasan narendasan left a comment

Choose a reason for hiding this comment

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

LGTM only suggestion is moving tests into a tests subdirectory or into the tests directory. Is optional.

@peri044 peri044 mentioned this pull request Jun 30, 2025
Closed
@chohk88 chohk88 mentioned this pull request Jul 3, 2025
Closed
7 tasks
@peri044 peri044 merged commit cf65477 into main Jul 3, 2025
69 of 85 checks passed
peri044 added a commit that referenced this pull request Jul 8, 2025
@peri044
feat: Refactor LLM model zoo and add KV cache support (#3527)
10ff9e1 
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
@peri044 peri044 mentioned this pull request Jul 8, 2025
Merged
7 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@zewenli98 zewenli98 zewenli98 left review comments

@github-actions github-actions[bot] github-actions[bot] requested changes

@narendasan narendasan narendasan approved these changes

Assignees

No one assigned

Labels

cla signed component: api [Python] Issues re: Python API component: conversion Issues re: Conversion stage component: dynamo Issues relating to the `torch.compile` or `torch._dynamo.export` paths component: runtime documentation Improvements or additions to documentation

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@peri044 @narendasan @zewenli98 @facebook-github-bot