https://derekwang2002.github.io/ai-intelligence/en/projects/kimi/ Material changes in AI models, agents, engineering and infrastructure, with primary sources and recommendations. en Mon, 02 Nov 2026 16:56:00 GMT https://derekwang2002.github.io/ai-intelligence/en/events/ev-20260826-05/ ev-20260826-05-published Sun, 30 Aug 2026 00:00:20 GMT New ADOPT <p>vLLM 0.28.0 (584 commits from 270 contributors, 76 new) is dominated by a Kimi-K3 performance push: Decode Context Parallel support, fused FlashKDA decode/prefill kernels, combined all-gathers with 1.5-3x kernel-level speedup, an adaptive speculative token budget delivering ~60% better DSpark TTFT, and optional shared-expert sharding saving ~17 GiB per GPU. DeepSeek V4 gets sparse MLA working end-to-end for plain decode, MTP and DSpark speculative decoding, plus AMD Quark NVFP4 and ROCm enablement. Other headline items: DFlash2 speculative decoding with a candidate selector, Model Runner V2 maturation (E/P/D disaggregation, weight offloading), tiered KV-cache offloading including disk, a Rust frontend with gRPC (protobuf schemas on Buf), and new defaults (max_num_batched_tokens 8192-&gt;16384, Mamba prefix caching on by default). Breaking changes: bitsandbytes support moved to an out-of-tree plugin, Transformers bumped to 5.15.0, deprecated APIs removed.</p><p>Recommendation: ADOPT</p><p>Sources: <a href="https://github.com/vllm-project/vllm/releases/tag/v0.28.0">vllm-project/vllm · releases / tag / v0.28.0</a></p>