Models & Labs
Together AI Launches Provisioned Throughput for Open Models
Together AI Bloghigh confidence
Why it matters
- →Provides a cost-effective alternative to proprietary models, reducing inference costs by up to 90%.
- →Offers predictable pricing and guaranteed capacity, crucial for production workloads.
- →Facilitates the adoption of open models in enterprise environments, enhancing scalability and reliability.
Together AI has introduced Provisioned Throughput, a new service offering reserved inference capacity for open models with token-based pricing and a 99% uptime SLA. This service aims to provide companies with a cost-effective and reliable alternative to proprietary models, offering up to 90% savings compared to models like Claude Opus 4.8. Provisioned Throughput is available for models such as MiniMax M3 and GLM-5.2, with capacity in North America and EMEA. This development is expected to facilitate the adoption of open models in production environments by providing predictable pricing and guaranteed capacity.
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.