#Open-source ecosystem

AIShanghai AI Lab's InternLM released Intern-Decision-2B, a multimodal structured decision model fine-tuned from Qwen3.5-2B that returns calibrated answer distributions for multiple questions in one forward pass. It averages 84.68 across listed benchmarks with a 0.437 Brier score and 33.28 ms mean latency on a single RTX 4090. Model weights, a Python DecisionEngine API, and GitHub code are available, with support for up to 16 questions and eight images.

AIInternLM released Intern-Decision-0.8B, a multimodal structured decision model fine-tuned from Qwen3.5-0.8B that scores answers to multiple questions in one forward pass. The model reports a 79.38 average score and a 33.98 ms mean latency on a single RTX 4090, with 0.8B, 2B, and 4B sizes available. It is accessed through a Python DecisionEngine API that returns calibrated probabilities rather than generating free-form text.

AICanvases in the GitHub Copilot app are customizable interfaces that you and the agent share, such as kanban boards, dashboards, or checklists. You create one by running /create-canvas and describing the workflow, what you can do in the interface, and what the agent can do. Changes made by either you or the agent appear immediately in the shared canvas, and completed canvases can be saved as reusable extensions.

AITogether AI says teams can access frontier open models through its API without managing underlying infrastructure, a point Ted Cui, its VP of Engineering and Inference Platform, made at Apsara Conference 2026. The company emphasizes reliable, fast inference as essential for this access.

AIvLLM has published a blog post explaining how its integration with TileRT works, alongside a public benchmark configuration in the InferenceX repository. The benchmark script covers GLM-5.3 FP8 on MI355X hardware and is linked on GitHub. The post itself provides the integration details.

AIThe TileRT and AMD teams reached 469 tok/s single-user decode for GLM-5.3 on 8× MI355X using vLLM. The setup disaggregates work, with vLLM handling prefill and TileRT handling latency-critical decode through vLLM's V1 connector interface. SemiAnalysis's AgentX benchmark reports the configuration at 470 TPS on GLM 5.3 (FP8), over 40% faster than GB300 TRTLLM using FP4.

AIHugging Face released SmolDataEnvs, more than 5,000 open-source RL environments aimed at real-world data science tasks. They target the gap between simple educational games and frontier-level benchmarks, especially for improving coding in models under 10B parameters. The environments are designed as a testbed for developing new RL methods such as GRPO or OPSD.

AIGitHub Security Lab describes the Fuzzing Taskflow, an LLM agent pipeline that identifies entrypoints, writes harnesses, runs AFL++, reads coverage reports, and triages crashes for C/C++ repositories. The agent makes decisions while MCP tools handle execution, and state is stored in a SQLite database. The post also warns that the taskflow runs AFL and build commands directly on the host, so it should be used only in disposable environments without elevated privileges.

Why it matters: The post explains how an LLM agent automates fuzzing steps like harness writing, coverage gap chasing, and crash triage, with a runnable workflow and design tradeoffs.

AIOdyssey launched Agora-2, a multi-agent world model that the company is making available for public experimentation. The post predicts such models will increasingly power applications in AI training, AI safety, robotics, autonomous vehicles, defense, energy, cybersecurity, and gaming.

AINVIDIA shared a blog post linking to a story about an open protein dataset, tagging Google DeepMind and EMBL-EBI. The post itself provides no further details about the dataset's contents, scale, or availability.

AIGoodfire Research introduces Block-Sparse Featurizers (BSF), which decompose model activations into subspaces rather than single directions. Applied to DINOv3 and Stable Diffusion XL, BSFs find interpretable multidimensional features that better explain activations and enable fine-grained steering. The authors report that most concepts they examined have a stable rank of about two to four dimensions.

AIAlex Wortega releases openjev, a family of Jev-style models at 0.8B, 2B, 4B, and 35B-A3B for reranking, grading, guardrails, and real-time game decisions. The models come with SGLang serving support, according to the post.

AILiquid AI released an experimental DSpark draft model for its LFM2.5-VL-3B vision-language model, delivering decoding throughput gains of up to 2.66× on GPUs and 3.13× on edge devices. The drafter adds about 280M parameters, an 8.9% increase in the deployed model's parameter count, and is available on Hugging Face with support in llama.cpp, SGLang, and MLX-VLM.

AIvLLM now supports Gumbel-max watermarking, which embeds a keyed signal into generated text without changing the expected token distribution. Detection requires the secret key and tokenizer, and the signal accumulates over longer outputs. Benchmarks on Qwen3.5-27B with MTP-3 show throughput changes between -1.1% and +2.0% across batch sizes, with no consistent slowdown.

AIGoogle Developers reproduced Ai2's Olmo 3 7B from scratch in MaxText on Google Cloud TPUs, covering both the stage-1 pre-training run and the stage-2 mid-training anneal. The match was checked on held-out C4 loss, an 8-task accuracy suite, multi-domain perplexity, and token-level KL, not just the training loss curve. The post also describes a data-loader bug that made training loss look better than the reference while held-out metrics did not move.

Why it matters: The post documents how a faithful reproduction was verified on held-out metrics, including a data bug that training loss alone would have hidden.

AIInferact says vLLM maintainers used megakernel optimization to reach 700 tokens per second per user on TPUv7 running Kimi K3. SemiAnalysis, which shared the work, reports this is 56% better performance than Nvidia's GB200 NVL72. Inferact links a full technical breakdown of the TPU megakernel work on its blog.

AIJulien Chaumond of Hugging Face posted a thank-you message to supporters of arXiv. The quoted arXiv post reports a $17.2 million multiyear investment from Simons Foundation International, Siegel Family Endowment, and XTX Markets.

AIUnsloth says local AI adoption in 2026 has grown far beyond its own predictions. The company also reports surpassing 500M model downloads on Hugging Face, with Qwen3.8-27B GGUF as its most-downloaded model ever. It says it is working on new features to make local AI faster and more accessible in the coming weeks.

AIThomas Dohmke argues that Git was built to track code, while the next forge must also capture how that code came to be, with humans and agents working together. He shares this view in a conversation with DevInterrupted, where the context behind code lives alongside it.

AISebastian Raschka argues the main appeal of open-source agent harnesses is not cost but the ability to inspect what they do on users' computers. The post frames transparency over local actions, rather than price, as the key advantage.

AIAlibaba's Qwen-Image-2.1 is now the top open-source model in both the Image Edit Arena and Text-to-Image Arena, according to Arena. In the Image Edit Arena it scored 1367 points, placing #16 overall and just 3 points behind GPT-Image-1.5-high-fidelity at #15.

AIUnsloth Desktop received a hotfix update adding image editing for Qwen-Image-2.1. The update also fixes diffusers update issues, GGUF loading failures for Qwen-Image, and black artifacts during diffusion on A100 and consumer GPUs. Users should receive a banner prompting them to update.

AIFireworks released ARCv3, a lossless compressor for BF16 weight-update deltas sent from trainers to RL rollout machines. Across 1,000 production RL deltas, ARCv3 produced payloads nearly 50% smaller than ARCv2, averaging about 0.19% of the BF16 weight size versus 0.36%. ARCv3 is available through the Fireworks Training API as fireworks-delta-compression.

AIComfyUI's update makes the MiniMax H3 video VAE encode up to about 2.2x faster and decode 1.4-2.7x faster, cutting a 1344x768, 129-frame round trip on an RTX 5090 from 24.3 to 12.7 seconds. The gains come from a fused encoder kernel enabled by default, fp16 accumulation support in a custom convolution, and an int8 decoder, and the source says the changes are visually lossless to the eye. Users need ComfyUI v0.36.0 or above, and the int8 VAE file is a drop-in replacement for the standard one.

AIDaniel Han says Qwen-Image-2.1 works in Unsloth Desktop through INT8, FP8, and GGUF builds, with Unsloth also releasing dynamic GGUFs for it. Pinned RAM offloading lets INT8 and FP8 fit under 6–8GB of VRAM while remaining relatively fast. The linked Unsloth post says the 7B model runs on 12GB VRAM and performs on par with Nano Banana 2.0.