2 Pull requests merged by 2 people

• Add ModernBert SequenceClassification

  #2796 merged Mar 8, 2025

• Allow ModernBert to be used to generate embeddings.

  #2791 merged Mar 3, 2025

1 Pull request opened by 1 person

• Add Qwen2.5 Instruct model

  #2797 opened Mar 8, 2025

3 Issues opened by 3 people

• Does candle gptq int8 faster than pytorch on CPU?

  #2795 opened Mar 7, 2025

• Support IBM Granite 3.2 Language Models (GraniteForCausalLM architecture)

  #2794 opened Mar 3, 2025

• Using Intel's mkl on Linux

  #2793 opened Mar 2, 2025

5 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Implement I-quants (IQ4XS, IQ4NL)

  #2785 commented on Mar 3, 2025 • 5 new comments

• Will candle support YOLOV5？

  #1858 commented on Mar 3, 2025 • 0 new comments

• Candle on Mobile

  #2787 commented on Mar 3, 2025 • 0 new comments

• Vulkan support

  #1810 commented on Mar 4, 2025 • 0 new comments

• Can I add Qwen Instruct models?

  #2792 commented on Mar 8, 2025 • 0 new comments