Skip to content
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.

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

Support Phi-4-mini and Phi-4-multimodal-instruct in LLM text-generation comps on gaudi mode #1335

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

XinyaoWa
Copy link
Collaborator

@XinyaoWa XinyaoWa commented Feb 26, 2025

Description

Add support for Phi-4 and Phi-4-multimodal-instruct with optimum habana, currently both need extra patch code.
microsoft/Phi-4-mini-instruct
microsoft/Phi-4-multimodal-instruct

Issues

List the issue or RFC link this PR is working on. If there is no such link, please mark it as n/a.

Type of change

List the type of change like below. Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds new functionality)
  • Breaking change (fix or feature that would break existing design and interface)
  • Others (enhancement, documentation, validation, etc.)

Dependencies

List the newly introduced 3rd party dependency if exists.

Tests

Describe the tests that you ran to verify your changes.

@XinyaoWa XinyaoWa changed the title Enhance LLM text-generation native on gaudi mode Support Phi-4 and Phi-4-multimodal-instruct in LLM text-generation comps on gaudi mode Feb 27, 2025
@XinyaoWa XinyaoWa changed the title Support Phi-4 and Phi-4-multimodal-instruct in LLM text-generation comps on gaudi mode Support Phi-4-mini and Phi-4-multimodal-instruct in LLM text-generation comps on gaudi mode Feb 27, 2025
@XinyaoWa XinyaoWa force-pushed the llm_gaudi_enhance branch 4 times, most recently from bce8e1a to 5dc223b Compare February 27, 2025 08:38
@XinyaoWa XinyaoWa requested a review from ZePan110 as a code owner February 27, 2025 08:38
@XinyaoWa XinyaoWa requested a review from Spycsh as a code owner February 27, 2025 13:18
Copy link

codecov bot commented Feb 27, 2025

Codecov Report

All modified and coverable lines are covered by tests ✅

Files with missing lines Coverage Δ
comps/cores/proto/api_protocol.py 96.15% <100.00%> (+0.01%) ⬆️

…mps on gaudi mode

Add support for phi-4 related model with optimum habana

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>
@XinyaoWa XinyaoWa force-pushed the llm_gaudi_enhance branch 2 times, most recently from f00f670 to 93be71a Compare February 28, 2025 02:28
@joshuayao joshuayao linked an issue Feb 28, 2025 that may be closed by this pull request
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.

[Feature] Model support: phi-4
1 participant