AI/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2024-09-19 15:25:53 +00:00
Code Issues Packages Projects Releases Wiki Activity
971c83d1d3
gpt4all/gpt4all-bindings/python/CHANGELOG.md
Jared Van Bortel 971c83d1d3
llama.cpp: pull in fix for Kompute-related nvidia-egl crash (#2843) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-08-13 11:10:10 -04:00

3.9 KiB
Raw Blame History

Changelog

All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog.

Unreleased

Changed

  • Search for pip-installed CUDA 11 as well as CUDA 12 (#2802)
  • Stop shipping CUBINs to reduce wheel size (#2802)
  • Use llama_kv_cache ops to shift context faster (#2781)
  • Don't stop generating at end of context (#2781)

Fixed

  • Make reverse prompt detection work more reliably and prevent it from breaking output (#2781)
  • Explicitly target macOS 12.6 in CI to fix Metal compatibility on older macOS (#2849)
  • Do not initialize Vulkan driver when only using CPU (#2843)
  • Fix a segfault on exit when using CPU mode on Linux with NVIDIA and EGL (#2843)

2.8.0 - 2024-08-05

Added

  • Support GPT-NeoX, Gemma 2, OpenELM, ChatGLM, and Jais architectures (all with Vulkan support) (#2694)
  • Enable Vulkan support for StarCoder2, XVERSE, Command R, and OLMo (#2694)
  • Support DeepSeek-V2 architecture (no Vulkan support) (#2702)
  • Add Llama 3.1 8B Instruct to models3.json (by @3Simplex in #2731 and #2732)
  • Support Llama 3.1 RoPE scaling (#2758)
  • Add Qwen2-1.5B-Instruct to models3.json (by @ThiloteE in #2759)
  • Detect use of a Python interpreter under Rosetta for a clearer error message (#2793)

Changed

  • Build against CUDA 11.8 instead of CUDA 12 for better compatibility with older drivers (#2639)
  • Update llama.cpp to commit 87e397d00 from July 19th (#2694)

Removed

  • Remove unused internal llmodel_has_gpu_device (#2409)
  • Remove support for GPT-J models (#2676, #2693)

Fixed

  • Fix debug mode crash on Windows and undefined behavior in LLamaModel::embedInternal (#2467)
  • Fix CUDA PTX errors with some GPT4All builds (#2421)
  • Fix mishandling of inputs greater than n_ctx tokens after #1970 (#2498)
  • Fix crash when Kompute falls back to CPU (#2640)
  • Fix several Kompute resource management issues (#2694)
  • Fix crash/hang when some models stop generating, by showing special tokens (#2701)
  • Fix several backend issues (#2778)
    • Restore leading space removal logic that was incorrectly removed in #2694
    • CUDA: Cherry-pick llama.cpp DMMV cols requirement fix that caused a crash with long conversations since #2694