Nicolas Patry
Nicolas Patry
What are you libraries versions ? It could be that or something import huggingface_hub before your environment modification leading to it not being discovered ?
In the end, we added support, but through explicit OPT-IN using `::from_env` initialization. https://github.com/huggingface/hf-hub/pull/85
This is not up to this library to add support for every environment variable that might exist in the HF ecosystem. This library enables overriding or supporting all flags if...
Done through `::from_env` method call (which isn't the default on purpose, using environment variables should be opt-in). https://github.com/huggingface/hf-hub/pull/85
This change doesn' seem to fix neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8 for me
I'm confused this still doesn't fix neural magic. ``` text-generation-launcher --model-id meta-llama/Meta-Llama-3-8B --quantize fp8 ``` is currently working on `main`. This might have been fixed by something else ? Can...
Closing as stale, feel free to reopen.
> 1. from 20x20px to 40x40px (meets qwens minimal requirement without hacky fix) I do not understand, why should we impose anything on the user for the images. If 20px...
Closing as stale. Feel free to reopen.
Which tests would you like me to add, batch_prefill_kernels ? others ? Wdym ref to build from source ? I am building already.