Models & Labs
vLLM v0.26.0 Release Enhances Model Support
vLLM Releaseshigh confidence
Why it matters
- →The new Inkling model family introduces advanced features for improved AI model performance.
- →Enhanced hardware support broadens the applicability of vLLM across different platforms.
- →Improved attention mechanisms and KV offloading increase efficiency for hybrid models.
vLLM has released version 0.26.0, featuring significant updates including the new Inkling model family with advanced CUDA graph support and speculative decoding. The release also enhances performance across multiple hardware platforms, such as AMD and XPU, with the DeepSeek-V4 performance push. Improvements in attention mechanisms and KV offloading provide greater flexibility for hybrid models. These updates make vLLM a more powerful tool for developers handling large-scale AI models.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
More from vLLM Releases
More in Models & Labs
Models & Labsother
llama.cpp b11193 adds Snapdragon Hexagon and ROCm 10
This release quietly expands llama.cpp's hardware support to include Qualcomm's Hexagon NPU on Linux arm64, a significant step for local inference on Snapdragon devices. It also updates CUDA builds to version 13.4 and introduces ROCm 10.0 binaries, keeping the project aligned with the latest NVIDIA and AMD driver ecosystems. KleidiAI on Apple Silicon is temporarily disabled in this build, likely due to stability checks rather than a feature rollback. For developers targeting edge AI or diverse GPU stacks, this update ensures broader compatibility without requiring custom compilation.
llama.cpp Releases
© Lev SelectorModels & Labsmodels
NVIDIA NVFP4 and SoL-Pi Token Efficiency
NVIDIA introduced the NVFP4 4-bit format and SoL-Pi technology, which uses 2x fewer tokens for improved efficiency.