Skip to content

[Model] use AutoWeightsLoader for olmoe,opt,orion,persimmon,phi3_small #16548

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 1 commit into from
Apr 17, 2025
Merged

[Model] use AutoWeightsLoader for olmoe,opt,orion,persimmon,phi3_small #16548

merged 1 commit into from
Apr 17, 2025

Conversation

@lengrongfu
Copy link
Contributor

@lengrongfu lengrongfu commented Apr 13, 2025 •
edited by github-actions bot
Loading

Issue: #15697

python3 -m vllm.entrypoints.cli.main serve allenai/OLMoE-1B-7B-0924-Instruct --trust-remote-code --gpu-memory-utilization 0.95

python3 -m vllm.entrypoints.cli.main serve facebook/opt-iml-max-1.3b --trust-remote-code --gpu-memory-utilization 0.95

python3 -m vllm.entrypoints.cli.main serve adept/persimmon-8b-chat --trust-remote-code --gpu-memory-utilization 0.95

python3 -m vllm.entrypoints.cli.main serve microsoft/Phi-3-small-8k-instruct --trust-remote-code --gpu-memory-utilization 0.95

python3 -m vllm.entrypoints.cli.main serve OrionStarAI/Orion-14B-Chat --trust-remote-code --gpu-memory-utilization 0.95

@github-actions
Copy link

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

@lengrongfu lengrongfu marked this pull request as ready for review April 16, 2025 07:16
@lengrongfu lengrongfu force-pushed the feat/new1-use-autoweights branch from a23571f to bfc8030 Compare April 16, 2025 07:35
@lengrongfu
Copy link
Contributor Author

@DarkLight1337 Please take a look.

DarkLight1337
DarkLight1337 reviewed Apr 16, 2025
View reviewed changes
DarkLight1337
DarkLight1337 reviewed Apr 16, 2025
View reviewed changes
DarkLight1337
DarkLight1337 reviewed Apr 16, 2025
View reviewed changes
@lengrongfu lengrongfu force-pushed the feat/new1-use-autoweights branch from bfc8030 to b0b8747 Compare April 16, 2025 15:06
DarkLight1337
DarkLight1337 reviewed Apr 16, 2025
View reviewed changes
@lengrongfu lengrongfu mentioned this pull request Apr 16, 2025
Open
1 task
@lengrongfu lengrongfu force-pushed the feat/new1-use-autoweights branch from b0b8747 to 2163bc0 Compare April 17, 2025 04:43
DarkLight1337
DarkLight1337 reviewed Apr 17, 2025
View reviewed changes
DarkLight1337
DarkLight1337 reviewed Apr 17, 2025
View reviewed changes
@lengrongfu lengrongfu force-pushed the feat/new1-use-autoweights branch from 2163bc0 to 0d85445 Compare April 17, 2025 15:26
DarkLight1337
DarkLight1337 reviewed Apr 17, 2025
View reviewed changes
DarkLight1337
DarkLight1337 approved these changes Apr 17, 2025
View reviewed changes
Copy link
Member

@DarkLight1337 DarkLight1337 left a comment •
edited
Loading

Choose a reason for hiding this comment

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

Thanks, let's merge this first before checking the other rotary_emb

@lengrongfu lengrongfu force-pushed the feat/new1-use-autoweights branch from 0d85445 to e6c8f9c Compare April 17, 2025 15:32
@DarkLight1337 DarkLight1337 added the ready ONLY add when PR is ready to merge/full CI is needed label Apr 17, 2025
@DarkLight1337 DarkLight1337 enabled auto-merge (squash) April 17, 2025 15:33
@DarkLight1337 DarkLight1337 merged commit 5125d72 into vllm-project:main Apr 17, 2025
59 of 62 checks passed
yangw-dev pushed a commit to yangw-dev/vllm that referenced this pull request Apr 21, 2025
@lengrongfu @yangw-dev
[Model] use AutoWeightsLoader for olmoe,opt,orion,persimmon,phi3_small (
facf397 
vllm-project#16548)

Signed-off-by: rongfu.leng <[email protected]>
Signed-off-by: Yang Wang <[email protected]>
jikunshang pushed a commit to jikunshang/vllm that referenced this pull request Apr 29, 2025
@lengrongfu @dbyoung18
[Model] use AutoWeightsLoader for olmoe,opt,orion,persimmon,phi3_small (
098c077 
vllm-project#16548)

Signed-off-by: rongfu.leng <[email protected]>
lk-chen pushed a commit to lk-chen/vllm that referenced this pull request Apr 29, 2025
@lengrongfu @lk-chen
[Model] use AutoWeightsLoader for olmoe,opt,orion,persimmon,phi3_small (
bf8eabc 
vllm-project#16548)

Signed-off-by: rongfu.leng <[email protected]>
adobrzyn pushed a commit to HabanaAI/vllm-fork that referenced this pull request Apr 30, 2025
@lengrongfu @adobrzyn
[Model] use AutoWeightsLoader for olmoe,opt,orion,persimmon,phi3_small (
849ffb7 
vllm-project#16548)

Signed-off-by: rongfu.leng <[email protected]>
Signed-off-by: Agata Dobrzyniewicz <[email protected]>
RichardoMrMu pushed a commit to RichardoMrMu/vllm that referenced this pull request May 12, 2025
@lengrongfu
[Model] use AutoWeightsLoader for olmoe,opt,orion,persimmon,phi3_small (
0a44a1f 
vllm-project#16548)

Signed-off-by: rongfu.leng <[email protected]>
Signed-off-by: Mu Huai <[email protected]>
@ckhordiasma ckhordiasma mentioned this pull request May 14, 2025
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@DarkLight1337 DarkLight1337 DarkLight1337 approved these changes

Assignees

No one assigned

Labels

ready ONLY add when PR is ready to merge/full CI is needed

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@lengrongfu @DarkLight1337