10000 vllm/llama-vision llava calibration infinite loop fix by WeiweiZhang1 · Pull Request #343 · intel/auto-round · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

vllm/llama-vision llava calibration infinite loop fix #343

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
Merged
merged 15 commits into from
Nov 26, 2024
Merged

vllm/llama-vision llava calibration infinite loop fix #343

merged 15 commits into from
Nov 26, 2024

Conversation

WeiweiZhang1
Copy link
Collaborator

No description provided.

@WeiweiZhang1
calib check func bugfix, refine get_dataloader
dfeb6a3 
Signed-off-by: Zhang, Weiwei1 <weiwei1.zhang@intel.com>
@WeiweiZhang1
fixtypo
67ca091 
Signed-off-by: Zhang, Weiwei1 <weiwei1.zhang@intel.com>
wenhuach21
wenhuach21 reviewed Nov 25, 2024
View reviewed changes
@wenhuach21 wenhuach21 changed the title calib check func bugfix, refine get_dataloader to support INC3.2 vllm/llama-vision llava calibration bug fix, refine get_dataloader to support INC3.2 Nov 25, 2024
@wenhuach21 wenhuach21 changed the title vllm/llama-vision llava calibration bug fix, refine get_dataloader to support INC3.2 vllm/llama-vision llava calibration bug fix Nov 25, 2024
wenhuach21
wenhuach21 reviewed Nov 25, 2024
View reviewed changes
@wenhuach21 wenhuach21 changed the title vllm/llama-vision llava calibration bug fix vllm/llama-vision llava calibration infinite loop fix Nov 25, 2024
wenhuach21
wenhuach21 reviewed Nov 25, 2024
View reviewed changes
wenhuach21
wenhuach21 reviewed Nov 25, 2024
View reviewed changes
@wenhuach21
Copy link
Contributor

remember to remind user to include this fix in the recipe of llama-vision

@WeiweiZhang1
bugfix
dfa9552 
Signed-off-by: Zhang, Weiwei1 <weiwei1.zhang@intel.com>
@WeiweiZhang1
refine log
62e4ab0 
Signed-off-by: Zhang, Weiwei1 <weiwei1.zhang@intel.com>
@wenhuach21 wenhuach21 changed the title vllm/llama-vision llava calibration infinite loop fix vllm/llama-vision llava calibration infinite loop fix stage 1 Nov 26, 2024
wenhuach21
wenhuach21 reviewed Nov 26, 2024
8000 View reviewed changes
@n1ck-guo
update
611af8a 
Signed-off-by: n1ck-guo <heng.guo@intel.com>
@n1ck-guo
update
0264064 
Signed-off-by: n1ck-guo <heng.guo@intel.com>
wenhuach21
wenhuach21 reviewed Nov 26, 2024
View reviewed changes
wenhuach21
wenhuach21 reviewed Nov 26, 2024
View reviewed changes
@wenhuach21 wenhuach21 changed the title vllm/llama-vision llava calibration infinite loop fix stage 1 vllm/llama-vision llava calibration infinite loop fix Nov 26, 2024
wenhuach21
wenhuach21 reviewed Nov 26, 2024
View reviewed changes
n1ck-guo and others added 3 commits November 25, 2024 22:17
@n1ck-guo
fix
dcfee92 
Signed-off-by: n1ck-guo <heng.guo@intel.com>
@pre-commit-ci
[pre-commit.ci] auto fixes from pre-commit.com hooks
0d1fb7d 
for more information, see https://pre-commit.ci
@n1ck-guo
fix
00df0bd 
Signed-off-by: n1ck-guo <heng.guo@intel.com>
wenhuach21
wenhuach21 reviewed Nov 26, 2024
View reviewed changes
@n1ck-guo
update
2d27811 
Signed-off-by: n1ck-guo <heng.guo@intel.com>
@n1ck-guo
Merge branch 'calib_bugfix' of https://github.com/intel/auto-round in…
e07994d 
…to calib_bugfix
wenhuach21
wenhuach21 reviewed Nov 26, 2024
View reviewed changes
@n1ck-guo
fix
ed4477f 
Signed-off-by: n1ck-guo <heng.guo@intel.com>
@n1ck-guo
add ut
143d9c6 
Signed-off-by: n1ck-guo <heng.guo@intel.com>
@n1ck-guo
fix
648877f 
Signed-off-by: n1ck-guo <heng.guo@intel.com>
wenhuach21
wenhuach21 reviewed Nov 26, 2024
View reviewed changes
auto_round/mllm/autoround_mllm.py
if quant_nontext_module and batch_size != 1:
logger.warning(f"batch_size({batch_size}) cannot be used for calibrating non-text modules,"
"reset to 1")
batch_size = 1
Copy link
Contributor

Choose a reason for hiding this comment

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

the gradient_accumualte should be changed too

@n1ck-guo
grad
a72171f 
Signed-off-by: n1ck-guo <heng.guo@intel.com>
@wenhuach21 wenhuach21 self-requested a review November 26, 2024 09:24
@wenhuach21 wenhuach21 merged commit a7fcb51 into main Nov 26, 2024
13 checks passed
@wenhuach21 wenhuach21 deleted the calib_bugfix branch November 26, 2024 09:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@n1ck-guo n1ck-guo n1ck-guo left review comments

@wenhuach21 wenhuach21 wenhuach21 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.
3 participants
@WeiweiZhang1 @wenhuach21 @n1ck-guo
0