llama-cpp — AI Digest

26 авг llama.cpp v0.3.0 — first tagged stable release of the b10621 nightly; dots3-note multimodal, GLM-4.5-Air MTP, DeepSeek 4 tensor-split, ggml v0.22.0 ggml-org tools
5 сен llama.cpp v0.4.0: lazy tensor reading, per-slot context limits, video input tools
17 июн llama.cpp June 16 Builds: Eagle3 Speculative Decoding, Vulkan UMA Memory, NVFP4 Fixes tools
22 июн llama.cpp b9754: Real-Time Model Load Progress via SSE and PEG Grammar Parser tools
29 июн llama.cpp Builds b9830–b9837: DFlash v2, MiniCPM5 Parser, --reasoning-preserve Flag ggml-org tools
8 июл Ollama v0.31.2: MLX small-batch matmul kernel, llama.cpp build 9840, CUDA updates tools
12 июл llama.cpp b9967–b9969: Adreno GPU Acceleration and OpenAI-Compatible Null Sampling tools
14 июл llama.cpp Adds Tencent Hunyuan 3, Minimax2 Eagle3 Speculative Decoding, and SYCL Fused MoE tools
19 авг llama.cpp ships v0.1.2 pre-release plus daily b10483–b10488 with SYCL perf fix, OpenVINO bump, DGX Spark CUDA tuning llama.cpp (GGML) tools
23 авг llama.cpp rolls up Aug 22 backend and model fixes tools
25 авг llama.cpp b10603-b10615 — GLM-4.5-Air MTP, Deepseek 4 -sm tensor, Metal flash-attn vec tuning for M1 Pro/M2 Ultra/M5 Max ggml-org tools
28 авг llama.cpp b10660 adds Qwen3.8-Flash-Next (qwen4exp) architecture: hyper-connections, gated delta net layers, MoE, PLE n-gram embedding llama.cpp tools
29 авг llama.cpp nightly burst b10668-b10679 includes Vulkan wrong-token fix llama.cpp tools
1 сен llama.cpp brings MTP speculative decoding to recurrent Qwen models ggml tools
2 сен llama.cpp Sep 1-2 wave: +4.9% generation from n-gram lookup fix, fused CUDA MoE reduction ggml tools
15 сен llama.cpp v0.4.1 adds Maple 20B, Tencent Hy 4, and Spark2.5 support ggml tools
17 сен llama.cpp patches remotely exploitable use-after-free in llama-server RPC endpoint ggml tools