Models & Labs
v0.19.1 Patch Release Announced
vLLM Releaseshigh confidence
Why it matters
- →The update improves the stability and performance of Gemma4 tools. • Bug fixes enhance user experience by addressing known issues. • Upgrading to Transformers v5.5.3 ensures compatibility with the latest features.
The v0.19.1 patch release has been announced, building on the previous version v0.19.0. This update includes an upgrade to Transformers v5.5.3 and addresses several bugs related to the Gemma4 tool, such as fixing invalid JSON in streaming tool calls and resolving issues with tool call corruption. Additionally, it introduces support for quantized MoE and Eagle3. These improvements aim to enhance the functionality and reliability of the Gemma4 system.
Read originalMore from vLLM Releases
More in Models & Labs
Models & Labsother
New release of llama.cpp b8991
The latest version b8991 of llama.cpp has been released, featuring updates for various operating systems.
llama.cpp Releases
Models & Labsother
llama.cpp update enhances compatibility and performance
The latest update to llama-mmap improves compatibility with various platforms and model sizes. Key enhancements include support for 32-bit wasm and updates to gguf.cpp style.
llama.cpp Releases
