Traditional inference wasn’t built for agentic coding. Agentic tools make hundreds of API calls per coding session, often with recomputed context, creating bottlenecks that drive up cost per token. NVIDIA Dynamo rebuilds the stack for agents with: → KV-aware routing →
@nvidiaai
-
Nemotron-Personas-Korea Tops Hugging Face Leaderboard
By
–
Super cool to see Nemotron-Personas-Korea hit #1 on @huggingface
. It's also the first Korean persona dataset. Huge shoutout to the team and the dev community pushing open datasets forward -
DeepSeek-V4-Pro Performance Benchmarks on NVIDIA Blackwell
By
–
Day 0 performance is here: DeepSeek-V4-Pro running on NVIDIA Blackwell Ultra. Using @vllm_project
's Day 0 recipe, we’ve captured the initial performance Pareto for DeepSeek’s flagship 1M long-context model. This curve highlights the baseline for balancing AI factory -
DeepSeek-V4-Pro 1.6T Model Now Available on NVIDIA Blackwell
By
–
Happy Friday!
— NVIDIA AI (@NVIDIAAI) 24 avril 2026
We just put DeepSeek-V4-Pro up on https://t.co/es07MrTxSs. It’s the world’s largest open source model at 1.6T parameters, and you can run it for free running on NVIDIA Blackwell GPUs.
Try the NVIDIA NIM API → https://t.co/zeWX4Y7Ipd pic.twitter.com/lNFsziIts4Happy Friday! We just put DeepSeek-V4-Pro up on http://
build.nvidia.com. It’s the world’s largest open source model at 1.6T parameters, and you can run it for free running on NVIDIA Blackwell GPUs. Try the NVIDIA NIM API → https://
build.nvidia.com/deepseek-ai/de
epseek-v4-pro?ncid=so-twit-300913
… -
DeepSeek V4 Pro Flash Day-0 vLLM Support Long-Context
By
–
Day-0 support for @deepseek_ai V4 Pro and Flash on vLLM — a new generation of DeepSeek model, purpose-built for tasks up to 1M tokens. Alongside the release, we're publishing a first-principles walkthrough of the new long-context attention and how we implemented it in vLLM. x.com/deepseek_ai/st…
-
DeepSeek V4 Launch with SGLang Optimizations and RL Pipeline
By
–
DeepSeek V4 by @deepseek_ai just dropped! SGLang is ready on Day 0 with a full stack of optimizations from architectures to low-level kernels. We also deliver a verified RL training pipeline in Miles (by @radixark) for V4 at launch: Native "ShadowRadix" Design: DeepSeek V4's
-
DeepSeek-V4 Million-Token Context LLM Agentic Workflows
By
–
DeepSeek-V4 is here — a million-token context, 1.6T parameter powerhouse optimized for agentic workflows. Out of the box, on DeepSeek-V4-Pro, NVIDIA Blackwell Ultra delivers over 150 TPS/user interactivity for agentic workflows. And we’re just getting started. Expect these
-
NVIDIA Advances Codex and GPT-5.5 Development at HQ
By
–
Codex + GPT-5.5 is moving fast here at NVIDIA HQ.
— NVIDIA AI (@NVIDIAAI) 23 avril 2026
We’ve even got our own Codex Lab for NVIDIANs to get started. https://t.co/PTqytJWp0f pic.twitter.com/zWnSnKfansCodex + GPT-5.5 is moving fast here at NVIDIA HQ. We’ve even got our own Codex Lab for NVIDIANs to get started.
-
OpenAI Launches GPT-5.5 with Advanced Agentic Coding Capabilities
By
–
Massive congrats to the team at @OpenAI 💚
— NVIDIA AI (@NVIDIAAI) 23 avril 2026
Moving the frontier forward isn’t easy, and GPT-5.5 does exactly that, with impressive performance across agentic coding, research tasks, and beyond. https://t.co/mGkM3VcPzqMassive congrats to the team at @OpenAI Moving the frontier forward isn’t easy, and GPT-5.5 does exactly that, with impressive performance across agentic coding, research tasks, and beyond.