Wang, Yi

[image_to_image_generation.py.txt](https://github.com/huggingface/optimum-habana/files/15451492/image_to_image_generation.py.txt) benchmark result with A100 **stabilityai/stable-diffusion-xl-refiner-1.0:** command in A100 python image_to_image_generation.py \ --model_name_or_path "stabilityai/stable-diffusion-xl-refiner-1.0" \ --src_image_path "https://raw.githubusercontent.com/timothybrooks/instruct-pix2pix/main/imgs/example.jpg" \ --prompts "turn him into cyborg" \ --num_images_per_prompt 1 \ --cuda \ --bf16...

**"lambdalabs/sd-image-variations-diffusers"** python image_to_image_generation.py \ --model_name_or_path "lambdalabs/sd-image-variations-diffusers" \ --src_image_path "https://github.com/SHI-Labs/Versatile-Diffusion/blob/master/assets/demo/reg_example/ghibli.jpg?raw=true" \ --num_images_per_prompt 1 \ --image_save_dir /tmp/stable_diffusion_images \ --guidance_scale 3 \ --bf16 \ --cuda Gaudi2 command python image_to_image_generation.py \ --model_name_or_path "lambdalabs/sd-image-variations-diffusers" \...

**timbrooks/instruct-pix2pix:** command in A100 python image_to_image_generation.py \ --model_name_or_path "timbrooks/instruct-pix2pix" \ --src_image_path "https://raw.githubusercontent.com/timothybrooks/instruct-pix2pix/main/imgs/example.jpg" \ --prompts "turn him into cyborg" \ --num_images_per_prompt 1 \ --batch_size 1 \ --guidance_scale 7.5 \ --image_guidance_scale 1...

try docker pull ghcr.io/huggingface/text-generation-inference:latest-intel-xpu and docker pull ghcr.io/huggingface/text-generation-inference:latest-intel-cpu

@danieldk @Narsil to comment,

no, I use https://github.com/huggingface/text-generation-inference/pull/2439 based branch, and have not seen such issue

I check the 3 failure cases and find they are related with the bug fix in https://github.com/huggingface/text-generation-inference/pull/2444/files#diff-d8aff332cf9104dd7460d2f53575239dc1f4bcdd374e575b8a504568bfc2e078R325. which will cause "Narsil/starcoder-gptq" 2 TP not to use exllama kernel. if you...

@Narsil to comment.

seems the failure is not related with the PR ERROR integration-tests/models/test_flash_medusa.py::test_flash_medusa_simple - RuntimeError: Launcher crashed ERROR integration-tests/models/test_flash_medusa.py::test_flash_medusa_all_params - RuntimeError: Launcher crashed ERROR integration-tests/models/test_flash_medusa.py::test_flash_medusa_load - RuntimeError: Launcher crashed

use VLLM multimodality benchmark to test tgi backend，find request loss issue because “：” is returned and json load fail