fix order, kompute whitelist, changelog entry,

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Add Granite arch to model and kompute whitelist
2026-07-17 10:58:08 +00:00 · 2025-02-12 14:16:57 -05:00 · 2025-02-12 19:17:03 +01:00
3 changed files with 5 additions and 1 deletions
--- a/gpt4all-backend/deps/llama.cpp-mainline
+++ b/gpt4all-backend/deps/llama.cpp-mainline
--- a/gpt4all-backend/src/llamamodel.cpp
+++ b/gpt4all-backend/src/llamamodel.cpp
@@ -53,6 +53,7 @@ static const std::vector<const char *> KNOWN_ARCHES {
    "gpt2",
    // "gptj", -- no inference code
    "gptneox",
+    "granite",
    "granitemoe",
    "mpt",
    "baichuan",
--- a/gpt4all-chat/CHANGELOG.md
+++ b/gpt4all-chat/CHANGELOG.md
@@ -6,6 +6,9 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).

 ## [Unreleased]

+### Added
+- Whitelist Granite (non-MoE) model architecture (by [@ThiloteE](https://github.com/ThiloteE) in [#3487](https://github.com/nomic-ai/gpt4all/pull/3487))
+
 ### Fixed
 - Fix several potential crashes ([#3465](https://github.com/nomic-ai/gpt4all/pull/3465))
 - Fix visual spacing issues with deepseek models ([#3470](https://github.com/nomic-ai/gpt4all/pull/3470))
Author	SHA1	Message	Date
Jared Van Bortel	0da05475e5	fix order, kompute whitelist, changelog entry, Signed-off-by: Jared Van Bortel <jared@nomic.ai>	2025-02-12 14:16:57 -05:00
ThiloteE	0a62c8fdb5	Add Granite arch to model and kompute whitelist Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>	2025-02-12 19:17:03 +01:00