6 Releases published by 1 person

• v0.3.11-metal

  published Jul 5, 2025

• v0.3.12-metal

  published Jul 6, 2025

• v0.3.12-cu124

  published Jul 6, 2025

• v0.3.12-cu121

  published Jul 6, 2025

• v0.3.12-cu122

  published Jul 6, 2025

• v0.3.12-cu123

  published Jul 6, 2025

2 Pull requests opened by 2 people

• ARM Runners support CUDA SBSA

  #2039 opened Jul 7, 2025

• Better chat format for Qwen2.5-VL

  #2040 opened Jul 8, 2025

2 Issues closed by 2 people

• Fail to install llama

  #2036 closed Jul 8, 2025

• Error calling `llama_kv_cache_clear` in llama.py with 0.3.10

  #2037 closed Jul 5, 2025

1 Issue opened by 1 person

• Inferencing Flan-T5 - GGML_ASSERT error

  #2038 opened Jul 7, 2025

3 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.

• llama_get_logits_ith: invalid logits id -1, reason: no logits

  #1812 commented on Jul 7, 2025 • 0 new comments

• Can't install with GPU support with Cuda toolkit 12.9 and Cuda 12.9

  #2013 commented on Jul 7, 2025 • 0 new comments

• Add support for Cohere Command models

  #2018 commented on Jul 3, 2025 • 0 new comments