Models & Labs
llama.cpp b9455 Release Adds Quantized KV Cache
llama.cpp Releaseshigh confidence
Why it matters
- →Quantized KV cache support improves model inference efficiency.
- →Fixes and adjustments enhance software stability and robustness.
- →Supports developers working with limited computational resources.
The b9455 release of llama.cpp brings quantized KV cache support, enhancing the efficiency of AI model inference. This update also fixes a partial view issue and removes an overly strict assert, contributing to the software's stability. The release includes builds for multiple platforms, though some configurations like macOS with KleidiAI and SYCL on Windows are disabled. This update is significant for developers aiming to optimize AI models for resource-constrained environments.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
What happened next
- 1llama.cpp b10068 release focuses on K/V cache
llama.cpp Releases · July 19, 2026 · Same story
- 2Llama.cpp b10985 Release Enhances Hash-Cache Efficiency
llama.cpp Releases · September 16, 2026 · Same story
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
