Skip to content

chore: Handle qwen2audio inputs ids expansion during processing - #3080

Merged
QiJune merged 4 commits into
NVIDIA:mainfrom
achartier:handle-qwen2audio-expansion
Mar 26, 2025
Merged

chore: Handle qwen2audio inputs ids expansion during processing#3080
QiJune merged 4 commits into
NVIDIA:mainfrom
achartier:handle-qwen2audio-expansion

Conversation

@achartier

Copy link
Copy Markdown
Collaborator

Transformers is expanding input_ids during processing since 4.48: huggingface/transformers#35534

Hence, it does not need to be done in TRT-LLM code anymore.

@achartier
achartier requested a review from symphonylyh March 25, 2025 21:47
@achartier

Copy link
Copy Markdown
Collaborator Author

/bot run

@niukuo

niukuo commented Mar 25, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #472 [ run ] triggered by Bot

@niukuo

niukuo commented Mar 25, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #472 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #405 completed with status: 'FAILURE'

Comment thread examples/qwen2audio/run.py Outdated
Signed-off-by: Aurelien Chartier <achartier@nvidia.com>
Signed-off-by: Aurelien Chartier <achartier@nvidia.com>
@achartier
achartier force-pushed the handle-qwen2audio-expansion branch from 9336b4c to 7e1d849 Compare March 25, 2025 23:55
@achartier

Copy link
Copy Markdown
Collaborator Author

/bot run

@niukuo

niukuo commented Mar 26, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #478 [ run ] triggered by Bot

@juney-nvidia juney-nvidia changed the title Handle qwen2audio inputs ids expansion during processing chore: Handle qwen2audio inputs ids expansion during processing Mar 26, 2025
@niukuo

niukuo commented Mar 26, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #478 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #411 completed with status: 'FAILURE'

Signed-off-by: Aurelien Chartier <achartier@nvidia.com>
@achartier

Copy link
Copy Markdown
Collaborator Author

/bot run

@niukuo

niukuo commented Mar 26, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #497 [ run ] triggered by Bot

@niukuo

niukuo commented Mar 26, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #497 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #429 completed with status: 'SUCCESS'

@QiJune

QiJune commented Mar 26, 2025

Copy link
Copy Markdown
Collaborator

/bot reuse-pipeline

@niukuo

niukuo commented Mar 26, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #530 [ reuse-pipeline ] triggered by Bot

@niukuo

niukuo commented Mar 26, 2025

Copy link
Copy Markdown
Collaborator

PR_Github #530 [ reuse-pipeline ] completed with state SUCCESS
Reusing PR_Github #497 for commit 5a91aab

@QiJune
QiJune merged commit 0ec7b57 into NVIDIA:main Mar 26, 2025
@achartier
achartier deleted the handle-qwen2audio-expansion branch March 26, 2025 12:59
wu1du2 pushed a commit to wu1du2/TensorRT-LLM that referenced this pull request May 11, 2025
…IA#3080)

* Handle qwen2audio inputs ids expansion during processing

Signed-off-by: Aurelien Chartier <achartier@nvidia.com>

* remove more dead code

Signed-off-by: Aurelien Chartier <achartier@nvidia.com>

* fix yapf

Signed-off-by: Aurelien Chartier <achartier@nvidia.com>

---------

Signed-off-by: Aurelien Chartier <achartier@nvidia.com>
Co-authored-by: QI JUN <22017000+QiJune@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants