Blog

Inkling

❖ Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages. Inkling is released with open weights to support research, fine-tuning and integration into third-party products by downstream developers.

Agents-A1

❖ Agents-A1 is a family of long-horizon Mixture-of-Experts agentic models (35B and 4B) that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling from two perspectives: scaling long-horizon trajectories and scaling heterogeneous agent abilities.

VeRL-Omni

❖ VeRL-Omni is a general RL training framework focused on multimodal generative models, built on top of verl (Volcano Engine Reinforcement Learning). It is designed to provide easy, fast, and stable RL training for diffusion and omni-modality models. verl is the open-source version of HybridFlow — a Flexible and Efficient RLHF Framework.

TorchTPU

❖ TorchTPU is an open-source, native PyTorch backend for Google Cloud TPUs, developed in collaboration between Google and the PyTorch team at Meta. With TorchTPU, developers can run existing PyTorch workloads on TPU hardware with minimal code changes and scale training and inference workloads from a single chip to multi-slice TPU pods.

CUDA Graphs in SGLang

❖ CUDA Graphs promise to remove kernel-launch overhead, but realizing that benefit in an inference engine requires graphing as much of the workload as possible without sacrificing compatibility, startup time, or memory. In SGLang, we refactored CUDA Graph support around a common runner/backend interface, making different capture strategies reusable across execution paths.

LongCat-2.0

❖ We introduce LongCat-2.0, a large-scale MoE language model with 1.6 trillion total parameters and ~48 billion activated per token — a substantial step up from previous LongCat models, accompanied by several architectural improvements. Both the full training run and the large-scale deployment are built entirely on AI ASIC superpods.

Agent Harnesses

❖ Curated, ranked list of AI agent harnesses (the runtimes that close the loop between a stateless model and the outside world), orchestration frameworks, and harness techniques for reliable agentic systems. 160+ harnesses · 12 categories · weekly-rescored · MCP-ready : claude mcp add agent-harnesses -- uvx agent-harnesses-mcp

❖ Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by approximately 30% compared with Kimi K2.6.