5 Releases published by 1 person

• v0.3.16-metal

  published Aug 15, 2025

• v0.3.16-cu121

  published Aug 15, 2025

• v0.3.16-cu124

  published Aug 15, 2025

• v0.3.16-cu122

  published Aug 15, 2025

• v0.3.16-cu123

  published Aug 15, 2025

2 Pull requests opened by 2 people

• Update hyperlink to llama.cpp build docs

  #2056 opened Aug 18, 2025

• Fix multi-sequence embeddings

  #2058 opened Aug 19, 2025

2 Issues closed by 2 people

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

  #2047 closed Aug 19, 2025

• cannot run fine-tuned gpt-oss model correctly

  #2053 closed Aug 16, 2025

2 Issues opened by 2 people

• Cannot install current version of llama-cpp-python 0.3.16 on Windows (backend independent)

  #2057 opened Aug 18, 2025

• cannot run fine-tuned gpt-oss model correctly

  #2054 opened Aug 16, 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.

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

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

• logprobs aren't returned if sampler will reach EOS

  #1528 commented on Aug 13, 2025 • 0 new comments

• Segmentation fault (core dumped) appearing randomly

  #2005 commented on Aug 19, 2025 • 0 new comments

• Can't compute multiple embeddings in a single call

  #2051 commented on Aug 19, 2025 • 0 new comments

• feat: Add Gemma3 chat handler (#1976)

  #1989 commented on Aug 17, 2025 • 0 new comments