🆕 [HF Models] ibm-granite - granite-vision-4.1-4b-GGUF


https://huggingface.co/ibm-granite/granite-vision-4.1-4b-GGUF

📰 Claude Blog - Building effective human-agent teams

https://claude.com/blog/building-effective-human-agent-teams


📰 Claude Blog - Agent identity in Claude Tag: a new access model for autonomous, team-wide AI

https://claude.com/blog/agent-identity-access-model


📰 Claude Blog - The full Claude Desktop experience on AWS, Google Cloud, and Microsoft Foundry

https://claude.com/blog/the-full-claude-desktop-experience-on-aws-google-cloud-and-microsoft-foundry

📰 Qwen Research - Qwen-AgentWorld: Language World Models for General Agents


https://qwen.ai/blog?id=qwen-agentworld

🔄 [GitHub Releases] flashinfer-ai/flashinfer - Release v0.6.13


https://github.com/flashinfer-ai/flashinfer/releases/tag/v0.6.13

🆕 [HF Models] LiquidAI - LFM2.5-230M

https://huggingface.co/LiquidAI/LFM2.5-230M


🔓 [HF Models] LiquidAI - LFM2.5-230M-GGUF

https://huggingface.co/LiquidAI/LFM2.5-230M-GGUF


🔓 [HF Models] LiquidAI - LFM2.5-230M-Base

https://huggingface.co/LiquidAI/LFM2.5-230M-Base

📰 PyTorch - TokenSpeed-Kernel: Portable APIs and High-Performance Kernels for Multi-Silicon LLM Inference
TL;DR The TokenSpeed-kernel is a standalone, open-source subsystem designed to solve backend complexity in LLM inference. It introduces a clean, layered API and registry system that decouples the high-level runtime...

https://pytorch.org/blog/lightseek-tokenspeed-kernel/

📰 HuggingFace - Which tokens does a hybrid model predict better?


https://huggingface.co/blog/allenai/hybrid-token-prediction


📰 HuggingFace - Run a vLLM Server on HF Jobs in One Command


https://huggingface.co/blog/vllm-jobs

📰 NVIDIA - Scaling AI Inference Across Multiple GPUs Using NVIDIA TensorRT with Multi-Device Inference Support
Generative AI workloads are rapidly outgrowing the memory and compute budget of single GPUs. For inference developers building media generation pipelines…

https://developer.nvidia.com/blog/scaling-ai-inference-across-multiple-gpus-using-nvidia-tensorrt-with-multi-device-inference-support/

🔓 [HF Models] nvidia - dlesym-v0-isccp-era5


https://huggingface.co/nvidia/dlesym-v0-isccp-era5

🆕 [HF Models] inclusionAI - Sing-Guard-0.8b-GGUF


https://huggingface.co/inclusionAI/Sing-Guard-0.8b-GGUF

🆕 [HF Models] Qwen - Qwen3-ForcedAligner-0.6B-hf

https://huggingface.co/Qwen/Qwen3-ForcedAligner-0.6B-hf


🆕 [HF Models] Qwen - Qwen3-ASR-0.6B-hf

https://huggingface.co/Qwen/Qwen3-ASR-0.6B-hf


🆕 [HF Models] Qwen - Qwen3-ASR-1.7B-hf

https://huggingface.co/Qwen/Qwen3-ASR-1.7B-hf

🆕 [GitHub Repos] orgs/NVIDIA - boro


https://github.com/NVIDIA/boro

🆕 [HF Models] nvidia - fast-foundationstereo


https://huggingface.co/nvidia/fast-foundationstereo

🆕 [HF Models] nvidia - c-fast-foundationstereo


https://huggingface.co/nvidia/c-fast-foundationstereo

📰 LMSys - Improving DeepEP MoE Load Balance in SGLang with Waterfill and LPLB


https://lmsys.org/blog/2026-06-26-waterfill-lplb

📰 Anthropic Research - Anthropic Economic Index report: Cadences


https://www.anthropic.com/research/economic-index-june-2026-report

📰 NVIDIA - Deploy a Production-Ready NVIDIA AI-Q Blueprint on Oracle Cloud Infrastructure
AI agents have changed a lot in the last two years. The first could only answer one question at a time. Then came multi-turn chat, where the model could keep…

https://developer.nvidia.com/blog/deploy-a-production-ready-nvidia-ai-q-blueprint-on-oracle-cloud-infrastructure/


📰 NVIDIA - Creating the NVIDIA Nemotron 3 Ultra NVFP4 Checkpoint with NVIDIA Model Optimizer
As context windows grow longer, moving large model weights efficiently becomes critical to performance. A common way to address this is quantization…

https://developer.nvidia.com/blog/creating-the-nvidia-nemotron-3-ultra-nvfp4-checkpoint-with-nvidia-model-optimizer/

🔄 [GitHub Releases] sgl-project/sglang - v0.5.14


https://github.com/sgl-project/sglang/releases/tag/v0.5.14

🆕 [HF Models] deepseek-ai - DeepSeek-V4-Pro-DSpark

https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-DSpark


🆕 [HF Models] deepseek-ai - DeepSeek-V4-Flash-DSpark

https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-DSpark

🆕 [GitHub Repos] orgs/deepseek-ai - DeepSpec


https://github.com/deepseek-ai/DeepSpec

🗓️ Weekly GitHub Activity


🦙 llama.cpp
└ Release: b9743 → b9828
└ 85 commits

- Added support for Step 3.5/3.7 flash MTP3 speculative decoding #24340,
Granite Speech Plus #24818,
LFM2.5-ColBERT-350M/Embedding-350M #24913,
Eagle3 Qwen3 draft models #24977,
Unlimited-OCR #24969
- Added SSE Replay Buffer to server and UI, allowing text generation to survive HTTP disconnects and resume seamlessly #23226
- Introduced real-time model loading progress tracking via SSE in both server and UI #24828 #24878
- Configured server to create checkpoints before every user message to improve session recovery #24176
- Redesigned the WebUI with a new logo, navigation cleanup, and significant mobile layout improvements #24897
- Enabled dual-GPU tensor parallelism on the SYCL backend via split-mode tensor #24152
- Overhauled Hexagon matrix multiplication kernels with tiled layouts, HVX/HMX microkernels, and graph caching #24954
- Upgraded OpenCL Flash Attention kernels for F16, F32, Q4_0, and Q8_0 #25069
- Moved server model downloading to a dedicated child process #24834
- Added CUDA fast path for strided 2D copies using cudaMemcpy2DAsync #25057
- Reduced synchronization overhead between CPU and CUDA async copies during split compute #20793
- Added 3D convolution support to Vulkan #24612
- Fixed CUDA integer overflows and transposed copy failures #24706 #25000
- Fixed incorrect vector dot computations on SVE-enabled ARM CPUs #24699

🔗 All changes | Latest release


🎨 stable-diffusion.cpp
└ Release: master-709-92a3b73 → master-721-8caa3f9
└ 12 commits

- Added support for Boogu image generation #1688
- Added support for Krea2 models #1705
- Introduced guidance_schedule support for generation control #1684
- Added logit-normal scheduler #1669
- Added --eager-load flag to pre-load parameters during model initialization #1687
- Added --prompt-file and --negative-prompt-file flags for file-based inputs #1693
- Fixed memory mapping by avoiding writable mmap for read-only weights #1698

🔗 All changes | Latest release


🤗 Fresh models trending on HuggingFace:

empero-ai/Qwythos-9B-Claude-Mythos-5-1M ♡488
krea/Krea-2-Turbo ♡310
krea/Krea-2-Raw ♡214
deepreinforce-ai/Ornith-1.0-9B ♡167
deepreinforce-ai/Ornith-1.0-35B ♡161
deepreinforce-ai/Ornith-1.0-397B ♡121
Chunjiang-Intelligence/DeepSeek-v4-Fable ♡112
hustvl/Moebius ♡51
AutoArk-AI/ARK-ASR-3B ♡37
paom/texture2albedo-v2 ♡32
SupraLabs/Supra-A2A-Nano-Exp ♡30
Gryphe/Gemma-4-26B-A4B-StyleTune-V2 ♡24
0xSero/GLM-5.2-504B ♡19
g-astruc/UniverSat ♡18
allenai/tmax-27b ♡18
ValiantLabs/Qwen3.6-27B-Esper4 ♡14
wikeeyang/Flux2-Klein-9B-True-V3 ♡14
vrgamedevgirl84/Krea2_Enhancer ♡12