Models & Labs
JetBrains Releases Mellum2: Efficient 12B MoE Model
Hugging Face Bloghigh confidence
Why it matters
- →Mellum2 offers significant efficiency improvements for latency-sensitive AI tasks.
- →The model's open-source nature allows for flexible deployment in private environments.
- →It exemplifies a shift towards specialized models that enhance larger AI systems.
JetBrains has introduced Mellum2, a 12 billion parameter Mixture-of-Experts model optimized for low-latency text and code workloads. The model activates only 2.5 billion parameters per token, achieving over twice the inference speed of comparable models. Mellum2 is open-source under the Apache 2.0 license and is designed for high-throughput tasks in software engineering, such as code generation and summarization. This release highlights a trend towards specialized models that improve the efficiency and control of AI systems without replacing existing components.
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.