vLLM has released version 0.29.0rc6, a release candidate focused on core stability and performance optimization. The primary change applies the dense prefix cache default to hybrid models, resolving previous inefficiencies in memory management for mixed-precision architectures. This update ensures that users of hybrid model configurations benefit from improved caching behavior without manual intervention. The release is part of the ongoing development cycle leading toward a stable v0.29.0 launch.
Read originalEarlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
Hugging Face Blog · June 26, 2026 · Background
vLLM Releases · June 30, 2026 · Same story
Hugging Face Blog · July 8, 2026 · Related
vLLM Releases · July 27, 2026 · Same story
llama.cpp Releases · August 28, 2026 · Related
llama.cpp Releases · October 12, 2026 · Related
vLLM v0.29.0 Release
2 developments