1:6397-alt1

- Update to b6397 (2025-09-06).
- Python-based model conversion scripts are sub-packaged. Note that they are
  not supported and are provided as-is.

.gear/llama.cpp.spec

@@ -11,7 +11,7 @@
 %def_with vulkan
 
 Name: llama.cpp
-Version: 6121
+Version: 6397
 Release: alt1
 Epoch: 1
 Summary: LLM inference in C/C++
@@ -71,12 +71,14 @@ Supported models:
    MoE, Smaug, Poro 34B, Bitnet b1.58 models, Flan T5, Open Elm models,
    ChatGLM3-6b + ChatGLM4-9b + GLMEdge-1.5b + GLMEdge-4b, SmolLM,
    EXAONE-3.0-7.8B-Instruct, FalconMamba Models, Jais, Bielik-11B-v2.3,
-   RWKV-6, QRWKV-6, GigaChat-20B-A3B, Trillion-7B-preview, Ling models
+   RWKV-6, QRWKV-6, GigaChat-20B-A3B, Trillion-7B-preview, Ling models,
+   LFM2 models, Hunyuan models
 
 Multimodal models:
 
    LLaVA 1.5 models, BakLLaVA, Obsidian, ShareGPT4V, MobileVLM 1.7B/3B
-   models, Yi-VL, Mini CPM, Moondream, Bunny, GLM-EDGE, Qwen2-VL
+   models, Yi-VL, Mini CPM, Moondream, Bunny, GLM-EDGE, Qwen2-VL,
+   LFM2-VL
 
 NOTE:
   MODELS ARE NOT PROVIDED. You'll need to download them from the original
@@ -274,6 +276,11 @@ llama-cli -m %_datadir/tinyllamas/stories260K.gguf -p "Once upon a time" -s 55 -
 %_datadir/%name/requirements*
 
 %changelog
+* Sat Sep 06 2025 Vitaly Chikunov <vt@altlinux.org> 1:6397-alt1
+- Update to b6397 (2025-09-06).
+- Python-based model conversion scripts are sub-packaged. Note that they are
+  not supported and are provided as-is.
+
 * Sat Aug 09 2025 Vitaly Chikunov <vt@altlinux.org> 1:6121-alt1
 - Update to b6121 (2025-08-08).
 

.gear/tags/list

@@ -1 +1 @@
-e54d41befcc1575f4c898c5ff4ef43970cead75f b6121
+186415d59552bd5c90549cd8e9be3cc287621fd9 b6397