#Together AI
35 articles with this tag
LLMs Fail to Write Fast Multi-GPU Kernels
Simran Arora from Together AI discusses the challenges of multi-GPU kernel development and why current LLMs struggle to optimize them, despite ongoing research.
AI Agents Discover New Science in "Einstein Arena"
James Zou of Together AI discusses how designing environments, rather than workflows, for AI agents can unlock creativity and lead to scientific breakthroughs, showcasing projects like the Einstein Arena and DSGym.
How Together AI Solves LLM Cold Starts
Together AI details native metrics and cold start benchmarks to fix nonlinear latency degradation in LLM autoscaling.
MiniMax M3: Open Source AI Model Deep Dive
Dan from Together AI and Olive from MiniMax discuss the open-sourcing of the M3 multimodal AI model, its capabilities, and the infrastructure behind scaling AI.
Together AI partners with Moonshot AI
Together AI partners with Moonshot AI to offer Kimi K3 and future models, providing developers with day-zero access to large-scale open-source AI.
Together AI Refines Model Deployment
Together AI details its capacity-aware routing architecture for dedicated model inference, enabling dynamic deployments, A/B testing, and efficient scaling.
99.9% Uptime: What It Really Means for AI Inference
Achieving 99.9% uptime for AI inference means surviving data center failures, demanding active multi-facility traffic and direct infrastructure control.
Together AI adds Inkling multimodal model
Together AI integrates Inkling, a new multimodal AI model from Thinking Machines Lab, offering text, image, and audio processing with controllable reasoning.
Together AI Boosts GPU Cluster Uptime
Together AI introduces major reliability and control upgrades for its GPU Clusters, including automated node repair and enhanced operational oversight.
Together AI Offers Predictable Inference
Together AI introduces Provisioned Throughput, offering reserved inference capacity for open models with token-based pricing and a 99% uptime SLA.
Four of every five dollars raised this week went to AI infrastructure. Here is what happened in the other 20 percent.
AI infrastructure took 79% of this week's $9.9B. Aramco led Together AI's $800M. Crusoe sought $3B. Schneider Electric paid $3.1B for Cognite.
Together AI lands $800M Series C
Together AI secures $800M Series C to accelerate open-source AI development, promising lower costs and higher performance for production workloads.
Open Source AI Beats Proprietary on Cost, Quality
Open-source AI models like Kimi K2.7 Code are proving to be cost-effective and quality-competitive alternatives to proprietary AI, especially with multimodal inputs.
Together AI Locks Down Enterprise Trust
Together AI achieves ISO 27001:2022 certification, enhancing trust and security for its enterprise AI platform and customer data.
Together AI Pushes LLM Context Limits to 5 Million Tokens
Max Ryabinin from Together AI discusses breaking barriers in LLM training, detailing techniques to achieve 5 million token context lengths and their impact on memory and performance.
Together AI Masters MiniMax M3 Inference
Together AI details engineering feats enabling efficient MiniMax M3 inference, unlocking 1M-token context and multimodality.
Rishabh Bhargava on Voice Agent Engineering
Rishabh Bhargava of Together AI discusses engineering voice agents, focusing on latency, quality, and scale challenges across STT, LLM, and TTS components.
Together AI's Speech-to-Text Speed Secret
Together AI reveals the engineering secrets behind its record-breaking speech-to-text performance, optimizing the entire data pipeline.
Coding Agent Inference Benchmark Revealed
Together AI unveils a new benchmark for coding agent inference, highlighting performance under real-world load and significant cost advantages.
Together AI Taps Blockchain for Cheaper AI
Together AI and Pearl Research Labs are integrating blockchain to cut AI inference costs, offering discounted model access subsidized by cryptocurrency mining.
Violin: AI Translates Video Content
Together AI launches Violin, an open-source AI tool for video translation and interactive content analysis.
Together AI Voice Finder Simplifies Voice Selection
Together AI's new Voice Finder tool allows developers to search over 600 voices using prompts or audio samples, simplifying voice selection for AI applications.
Together AI: Deploy Any Hugging Face Model Instantly
Together AI's Dedicated Container Inference lets developers deploy any Hugging Face model instantly, bypassing complex setups and accelerating AI experimentation.
DeepSeek-V4: Million-Token Context is a Serving Problem
DeepSeek-V4's million-token context window presents an inference systems challenge, demanding sophisticated cache management and serving strategies to unlock its potential.
Together AI Supercharges LLM Inference
Together AI unveils ATLAS, accelerating LLM inference up to 4x with adaptive speculative decoding, tackling the growing cost challenge for AI-native companies.
Together AI Halts Copy Fail Exploit
Together AI swiftly contained the Copy Fail CVE-2026-31431 vulnerability by disabling a vulnerable Linux kernel module, safeguarding its AI infrastructure.
Together AI partners with Adaption
Together AI and Adaption partner to integrate fine-tuning into data optimization, streamlining AI model development for open-source models.
DeepSeek V4 Pro Hits Together AI
Together AI launches DeepSeek V4 Pro, a 1.6T MoE model with a 512K context window and new cached input pricing for cost-effective long-context reasoning.
Together AI Adds NVIDIA Nemotron 3
Together AI launches NVIDIA's Nemotron 3 Nano Omni, a unified multimodal AI model, to developers, simplifying agentic application creation.
Together AI Slashes RL Training Time
Together AI's new distribution-aware speculative decoding slashes RL training time by up to 50%, tackling a major bottleneck in LLM post-training.
Shared GPUs, Zero Conflict
Together AI's multi-tenant GPU clusters offer a path to cost-effective, scalable AI compute without sacrificing team isolation.
AI Agents Collaborate to Solve Math Problems
Together AI's EinsteinArena platform enables AI agents to collaborate on complex scientific problems, achieving new breakthroughs in mathematics.
Together AI's Aurora Learns on the Fly
Together AI's Aurora framework uses RL to continuously adapt speculative decoding for faster LLM inference, outperforming static models.
Divide and Conquer LLMs Beat Giants
Smaller LLMs using a 'Divide & Conquer' strategy can outperform top models like GPT-4o on long context tasks, offering cost and speed benefits.
Mamba-3: Inference-First SSMs Arrive
Together AI's Mamba-3 advances state space models with a focus on inference speed, outperforming previous versions and some Transformers.