DSpark

This release introduces significant performance optimizations for Kimi-K3 and DeepSeek V4, alongside advancements in speculative decoding and Model Runner V2 maturation. It also features a new Rust frontend and gRPC capabilities, tiered KV cache offloading, and expanded model support.

This release introduces confidence-scheduled verification for DSpark spec decoding, enhancing its verification capabilities.

vLLM v0.27.0 introduces Kimi K3 support, new model additions like Qwen3.5 and VaultGemma, and a significant upgrade to PyTorch 2.13.0. The release also enhances performance and features across various areas including FlashAttention 4, Model Runner V2, KV offloading, and hardware enablement.

vLLM v0.25.0 introduces Model Runner V2 as the default for dense models, significantly improving performance and adding support for new features like EVS and realtime embeddings. The release also deprecates PagedAttention and enhances the Transformers backend to match native vLLM speed, alongside numerous model additions and performance optimizations across various hardware platforms.

llama.cpp 0.3.0 introduces multimodal capabilities with the dots3-note model and MTP support for GLM-4.5-Air, alongside significant updates to ggml and core model handling.

This release introduces support for DSpark for bailingmoe3. It also provides various pre-compiled binaries for different operating systems and hardware configurations.