Skip to content

Ipex compatible #12

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
Open
wants to merge 7 commits into
base: main
Choose a base branch
from
Open

Ipex compatible #12

wants to merge 7 commits into from

Conversation

jikunshang
Copy link
Owner

@jikunshang jikunshang commented May 9, 2025 •
edited by github-actions bot
Loading

No description provided.

jikunshang added 7 commits May 6, 2025 07:50
@jikunshang
add v1 xpu support
4c84c62 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

some v1 fixes

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

remove useless file

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

remove

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

add V1 test and set spawn in docker env

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

add missing dependency

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

fix test

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

update api name

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

update api

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

update default block size for v1

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

update memory usage

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

fix rebase issues

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

fix rebase, spec decode meta set to none

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

add xpu v1 config check

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

add mem log

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

fix init cache

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

add xpu profiler for V1

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

update rebase issue

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

update prepare_inputs for perf

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

update

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

refine xpu_model_runner

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
@jikunshang
fix sampler, attn metadata
e3ba9e5 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
@jikunshang
fix rebase issues
60c3d9e 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
@jikunshang
reuse gpu_runner
bc96239
@jikunshang
fix cuMemAllocator
f0fc0bd 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
@jikunshang
reuse init_device
cf7b8f2 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
@jikunshang
use ipex.compatible_mode
191886a 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
@github-actions GitHub Actions
Copy link

github-actions bot commented May 9, 2025

👋 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.

🚀

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@jikunshang