optimum-intel
optimum-intel copied to clipboard
🤗 Optimum Intel: Accelerate inference with Intel optimization tools
Following https://github.com/huggingface/optimum/pull/2023
The ipex patching is a common optimization for all tasks, so we can remove the task limitation.
# What does this PR do? in same cases optimum cli failed to export models due to inability to save config because it may contains some extra arguments, I added...
**Optimum creates a wrong chat_template config when running on linux.** Using optimum-cli to conver llama 3.1 8b to int4 compression, the model fails to run using [samples from genai repo](https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/python/chat_sample)....
# What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks...
# What does this PR do? Enables conversion and inference for multimodality llm like llava, llava-next, falcon-vl Example of usage: ``` from PIL import Image import requests from optimum.intel.openvino import...
# What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks...