2 Pull requests opened by 2 people

• Fix disk-cache LRU logic

  #2025 opened Jun 3, 2025

• Remove llama_kv_cache_view and deprecations were deleted on llama.cpp side too

  #2030 opened Jun 13, 2025

1 Issue closed by 1 person

• Build is broken in fedora 42 arm64

  #2024 closed Jun 3, 2025

5 Issues opened by 5 people

• Gemma 3:4B Multimodal CLIP Error [WinError -529697949] Windows Error 0xe06d7363

  #2031 opened Jun 17, 2025

• Access Violation issue facing for exe created using pyinstaller

  #2029 opened Jun 13, 2025

• Building and installing llama_cpp from source for RTX 50 Blackwell GPU

  #2028 opened Jun 13, 2025

• llama_cpp/lib/libllama.so: undefined symbol: llama_kv_cache_view_init

  #2026 opened Jun 3, 2025

• Support for jinja for custom chat templates

  #2023 opened May 22, 2025

19 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.

• Feat: Support Ranking Method

  #1820 commented on Jun 2, 2025 • 1 new comment

• Add support for Cohere Command models

  #2018 commented on May 23, 2025 • 0 new comments

• Added support for overriding tensor buffer types

  #2007 commented on May 22, 2025 • 0 new comments

• feat: Add Gemma3 chat handler (#1976)

  #1989 commented on Jun 6, 2025 • 0 new comments

• Initial commit

  #1978 commented on May 31, 2025 • 0 new comments

• pyinstaller hook script

  #709 commented on May 23, 2025 • 0 new comments

• Tool parser cannot analysis tool calls string from qwen2.5.

  #1784 commented on Jun 19, 2025 • 0 new comments

• When multiple requests are processed, the first request is interrupted

  #867 commented on Jun 18, 2025 • 0 new comments

• How to improve GPU utilization

  #1674 commented on Jun 13, 2025 • 0 new comments

• Does it support the gguf format model of Qwen2-VL-2B-Instruct

  #1895 commented on Jun 8, 2025 • 0 new comments

• llama-cpp-python 0.3.8 with CUDA

  #2010 commented on Jun 7, 2025 • 0 new comments

• ValueError: Failed to create llama_context

  #1304 commented on Jun 6, 2025 • 0 new comments

• Fail to install llama-cpp-python

  #738 commented on Jun 3, 2025 • 0 new comments

• Add reranking support

  #1794 commented on Jun 2, 2025 • 0 new comments

• Wheel build showing error of cmake suddenly - building version 0.2.76 on windows

  #1664 commented on Jun 2, 2025 • 0 new comments

• Retrieve attention score for all input tokens per generated token

  #1141 commented on Jun 1, 2025 • 0 new comments

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

  #2013 commented on May 27, 2025 • 0 new comments

• Feature request: add support for streaming tool use

  #1883 commented on May 25, 2025 • 0 new comments

• Include usage key in create_completion when streaming

  #1498 commented on May 23, 2025 • 0 new comments