chat: add release notes for v3.2.0 and bump version (#2847)

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

gpt4all-chat/CHANGELOG.md

@@ -4,7 +4,7 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 
-## [Unreleased]
+## [3.2.0] - 2024-08-12
 
 ### Added
 - Add Qwen2-1.5B-Instruct to models3.json (by [@ThiloteE](https://github.com/ThiloteE) in [#2759](https://github.com/nomic-ai/gpt4all/pull/2759))
@@ -23,6 +23,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
   - CUDA: Cherry-pick llama.cpp DMMV cols requirement fix that caused a crash with long conversations since [#2694](https://github.com/nomic-ai/gpt4all/pull/2694)
 - Make reverse prompt detection work more reliably and prevent it from breaking output ([#2781](https://github.com/nomic-ai/gpt4all/pull/2781))
 - Disallow context shift for chat name and follow-up generation to prevent bugs ([#2781](https://github.com/nomic-ai/gpt4all/pull/2781))
+- Explicitly target macOS 12.6 in CI to fix Metal compatibility on older macOS ([#2846](https://github.com/nomic-ai/gpt4all/pull/2846))
 
 ## [3.1.1] - 2024-07-27
 
@@ -82,6 +83,6 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 - Fix several Vulkan resource management issues ([#2694](https://github.com/nomic-ai/gpt4all/pull/2694))
 - Fix crash/hang when some models stop generating, by showing special tokens ([#2701](https://github.com/nomic-ai/gpt4all/pull/2701))
 
-[Unreleased]: https://github.com/nomic-ai/gpt4all/compare/v3.1.1...HEAD
+[3.2.0]: https://github.com/nomic-ai/gpt4all/compare/v3.1.1...v3.2.0
 [3.1.1]: https://github.com/nomic-ai/gpt4all/compare/v3.1.0...v3.1.1
 [3.1.0]: https://github.com/nomic-ai/gpt4all/compare/v3.0.0...v3.1.0

gpt4all-chat/CMakeLists.txt

@@ -18,9 +18,9 @@ endif()
 
 set(APP_VERSION_MAJOR 3)
 set(APP_VERSION_MINOR 2)
-set(APP_VERSION_PATCH 0)
+set(APP_VERSION_PATCH 1)
 set(APP_VERSION_BASE "${APP_VERSION_MAJOR}.${APP_VERSION_MINOR}.${APP_VERSION_PATCH}")
-set(APP_VERSION "${APP_VERSION_BASE}")
+set(APP_VERSION "${APP_VERSION_BASE}-dev0")
 
 list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/cmake/Modules")
 

gpt4all-chat/metadata/release.json

@@ -953,6 +953,40 @@
 * Jared Van Bortel (Nomic AI)
 * Shiranui (@supersonictw)
 * Community (beta testers, bug reporters, bindings authors)
+"
+  },
+  {
+    "version": "3.2.0",
+    "notes":
+"
+<b>&mdash; What's New &mdash;</b>
+* Translations for Simplified Chinese, Traditional Chinese, Italian, Portuguese, Romanian, and Spanish
+* Significantly faster context recalculation when context runs out
+* Models no longer stop generating when they run out of context
+* Add Qwen2-1.5B-Instruct to the model list
+
+<b>&mdash; Fixes &mdash;</b>
+* Fix a CUDA crash with long conversations since v3.1.0
+* Fix \"file(s)\" and \"word(s)\" appearing in UI instead of proper plurals
+* Show the correct icons for LocalDocs sources with uppercase extensions
+* More reliable reverse prompt detection
+* Fix a minor prompting issue introduced in v3.1.0
+* Disallow context shift for chat name and follow-up generation
+* Fix potential incompatibility with macOS 12 and 13
+",
+    "contributors":
+"
+* Jared Van Bortel (Nomic AI)
+* Adam Treat (Nomic AI)
+* Riccardo Giovanetti (`@Harvester62`)
+* Victor Emanuel (`@SINAPSA-IC`)
+* Jeremy Tayco (`@jstayco`)
+* Shiranui (`@supersonictw`)
+* Thiago Ramos (`@thiagojramos`)
+* ThiloteE (`@ThiloteE`)
+* Dominik (`@cosmic-snow`)
+* Jack (`@wuodoo`)
+* Community (beta testers, bug reporters, bindings authors)
 "
   }
 ]