Models & Labs
Together AI Launches Preemptible Compute for GPU Clusters
Together AI Bloghigh confidence
Why it matters
- →Provides a cost-effective solution for running non-critical workloads.
- →Enhances resource efficiency by utilizing unused capacity.
- →Offers flexibility in managing cloud computing resources.
Together AI has announced the public preview of preemptible compute for its GPU clusters, available on Kubernetes clusters across all regions. This new feature allows users to run interruption-tolerant workloads at half the cost of standard nodes, using the same NVIDIA accelerated infrastructure. Preemptible nodes are billed sub-hourly and can be reclaimed when capacity is needed elsewhere, making them ideal for short experiments and batch jobs. This development offers a cost-effective way to manage non-critical workloads, enhancing resource efficiency in cloud computing.
Read originalMore from Together AI Blog
.png)
More 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.