Models & Labs
Together AI's Inference Engine Outperforms Competitors
Together AI Bloghigh confidence
Why it matters
- →Together AI's engine significantly improves performance in high-concurrency coding agent workloads.
- →The benchmark addresses real-world production challenges, offering more relevant insights than traditional single-user tests.
- →This advancement can lead to substantial cost savings and efficiency gains for developers using coding agents.
Together AI has released benchmark results showing its Inference Engine outperforms competitors in coding agent workloads. The engine delivers 31% more tokens per second than the next fastest open-source engine, thanks to optimizations like ThunderMLA and custom kernel rewrites. The benchmark simulates real-world production scenarios with high concurrency and long input contexts. This advancement allows coding agents to manage higher loads more efficiently, reducing latency and operational costs.
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.