Infrastructure12d ago
SGLang Introduces Elastic EP with NIXL: Dynamic Live MoE Scaling Without Restarts or Traffic Draining
LMSYS Org in collaboration with the NVIDIA Dynamo team officially unveiled Elastic Expert Parallelism (Elastic EP) with NIXL backend integration in SGLang (@lmsysorg). Addressing the critical vulnerability of large-scale MoE deployments (such as DeepSeek-V3/V4) where static EP causes entire cluster crashes upon single-node failures and prevents live capacity resizing, Elastic EP decouples rigid expert-to-GPU bindings. Leveraging NVIDIA NIXL device APIs and Mooncake orchestrators, SGLang enables live scaling of active MoE serving deployments (e.g. dynamically expanding from 20 to 24 GPUs) without draining traffic or restarting clusters, while delivering resilient fault tolerance.
Tooling39d ago
Official DeepSeek Harness Desktop App Released: Bundles Cordis Plugin Core for Daemon-Free Local Agent Workflows
DeepSeek AI (@deepseek_ai) has officially launched the standalone desktop application for DeepSeek Harness (dsh) across macOS and Windows. Designed to eliminate the engineering overhead of managing CLI background daemons and local sandbox sockets, DeepSeek Harness Desktop integrates the web UI, the Cordis plugin execution engine, and isolated sandboxing into a native local client. It delivers out-of-the-box support for visual trajectory playback, arbitrary session branching, and multi-model sub-agent delegations.
Tooling39d ago
Knowledge Pull Requests (KPRs) Released: Bringing Git PR Workflows to LLM Knowledge Bases
Researchers from Johns Hopkins University have introduced Knowledge Pull Requests (KPRs, arXiv: 2609.26634), an interpretable framework for continual document authoring. Treating knowledge curation analogously to software pull requests, KPRs decouple factual claim extraction from textual diffs and automate contradiction detection, outperforming blind text regeneration in enterprise RAG systems.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.