5 Releases published by 1 person

• v0.3.15-metal

  published Aug 7, 2025

• v0.3.15-cu124

  published Aug 7, 2025

• v0.3.15-cu121

  published Aug 7, 2025

• v0.3.15-cu123

  published Aug 7, 2025

• v0.3.15-cu122

  published Aug 7, 2025

1 Pull request merged by 1 person

• fix: rename op_offloat to op_offload in llama.py

  #2046 merged Aug 7, 2025

2 Issues closed by 2 people

• Setting temperature to 100000000000000000 does not affect output.

  #1773 closed Aug 10, 2025

• add support for MXFP4 quantization to enable use of new gpt-oss models by OpenAI

  #2048 closed Aug 8, 2025

2 Issues opened by 2 people

• Can't compute multiple embeddings in a single call

  #2051 opened Aug 8, 2025

• Can't disable CMAKE ARG on Apple: GGML_METAL=OFF

  #2050 opened Aug 8, 2025

8 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.

• Pre-built cpu wheel does not work on Ubuntu due to libc.musl dependency

  #1628 commented on Aug 6, 2025 • 0 new comments

• Build fails on Windows with non-CUDA backends (CLBlast, Vulkan) for versions >= 0.2.78

  #2047 commented on Aug 10, 2025 • 0 new comments

• Windows11：ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (llama-cpp-python)

  #2035 commented on Aug 11, 2025 • 0 new comments

• Regression in unified KV cache appears after `llama.cpp` release b5912 in b5913

  #2045 commented on Aug 13, 2025 • 0 new comments

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

  #2013 commented on Aug 13, 2025 • 0 new comments

• Support multiple chat templates - step 2

  #1440 commented on Aug 8, 2025 • 0 new comments

• Chat template rendering extensions to match transformers

  #1486 commented on Aug 8, 2025 • 0 new comments

• Support LoRA hotswapping and multiple LoRAs at a time

  #1817 commented on Aug 11, 2025 • 0 new comments