Models & Labs
Gemma 4 Boosts Speed with Multi-Token Prediction
Ollama Bloghigh confidence
Why it matters
- →Multi-token prediction significantly enhances the speed of AI models, particularly for coding tasks.
- →The update improves responsiveness in coding agents, making them more efficient.
- →This advancement demonstrates a practical application of AI optimization techniques in real-world scenarios.
Ollama has released an update for Gemma 4, significantly increasing its speed on Apple Silicon by nearly 90% through multi-token prediction. This update is particularly beneficial for coding agents, as it allows the model to predict and verify multiple tokens simultaneously, enhancing responsiveness. The speedup is achieved by using a small draft model to propose tokens, which the main model then verifies in a single pass. This improvement requires no configuration from users and maintains the model's output integrity. The update is available in Ollama 0.31, marking a substantial advancement in AI-driven coding efficiency.
Read originalMore in Models & Labs
Models & Labsmodels
llama.cpp b10955 release addresses heap corruption
The latest release of llama.cpp, b10955, tackles a critical issue of heap corruption by disabling the ggml-cpu precompiled header and fixing CACHE_LINE_SIZE ambiguity. This update ensures consistent CACHE_LINE_SIZE values across C++ kernels and C work-buffer sizing code, preventing heap-buffer-overflow and subsequent crashes. By restoring the natural include order and removing the std::hardware_destructive_interference_size branch, the update makes the value deterministic and include-order independent. This release is a technical fix that stabilizes the runtime environment for developers using llama.cpp.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10956 release enhances SYCL backend
The latest llama.cpp release, b10956, introduces significant improvements to the SYCL backend, particularly for handling large k values in TOP_K operations. By implementing a radix select method, the update allows for efficient GPU-resident processing, avoiding previous limitations that forced operations to fall back to the CPU. This change enhances performance, especially in scenarios requiring large k values, such as qwen4exp's sparse-attention indexer. The update ensures that operations are more efficient and scalable, providing a notable boost in processing speed without regressing any measured shapes.