Search: “together-ai--x”

Aurora is a unified training-serving system that integrates reinforcement learning with adaptive speculative training to optimize large language model inference and training efficiency. The system dyn

Untied Ulysses is a memory-efficient technique for context parallelism that processes attention heads in chunks rather than sequences, reducing memory overhead during transformer inference and trainin

Opportunistic Expert Activation (OEA) is a batch-aware expert routing technique for mixture-of-experts models that enables faster decoding without requiring model retraining. The method optimizes whic

ParallelKernelBench is a benchmarking framework designed to evaluate large language models' ability to generate optimized GPU kernels for multi-GPU computing environments. The benchmark assesses LLMs

Together AI advocates for democratizing artificial intelligence by making it abundant and affordable rather than concentrated among expensive proprietary systems. The post likely argues for open-sourc

Together AI is promoting a rescheduled presentation about sparse attention mechanisms and kernel optimizations in collaboration with MiniMax AI, scheduled for 10:45am PT. The session focuses on techni

Multi-GPU kernels are the real test for coding models. Today at @aiDotEngineer, @simran_s_arora shared ParallelKernelBench, an open-source benchmark for evaluating whether LLMs can write fast CUDA ker

Nemotron 3 Ultra is taking off on Together AI 🚀 In just days, it's climbed to 35B tokens/day on @OpenRouter. That's the community voting with their tokens for open models that are fast, efficient, and

Our research team has 9 papers at ICML next week! Spanning the full stack from frontier agents to GPU kernels, we're excited to share what our researchers and collaborators have been working on. If yo

Together AI announced their Series C funding round, which was covered in a reporting piece by the New York Times. The announcement was shared via their official X (formerly Twitter) account, linking t

Together AI announced a Series C funding round and shared details about their company vision, current capabilities, and future direction in open-source AI development and inference optimization. The a

ParallelKernelBench is a benchmark tool or methodology developed by Together AI for evaluating the performance of parallel kernel execution in machine learning systems. The benchmark likely measures m

Together AI is announcing their participation in ICML 2026 (International Conference on Machine Learning) and inviting the community to visit them at the conference. The announcement likely includes d

Tasks moved from closed models to open models on Together AI cost one-fifth to one-seventh as much. That's from @DecagonAI co-founder @AshwinSreenivas in the NYT today. This is what abundant intellige

Together AI presented a 2-hour technical deep dive on building inference engines capable of handling trillion-token agentic workloads, covering architecture and optimization strategies for large-scale

As open models get stronger, more workloads move into the competitive inference market. That pushes the real fight toward speed, cost, reliability, and control. Together AI is where open models become

Open models are not just a pricing story. They are what happens when the AI stack becomes modular: models, APIs, harnesses, tools, and inference all improving independently. Together AI is building th

Together AI announced a submission portal for winners at aicup.io, crediting @nutlope and @federicobianchy for creating the initiative. This appears to be related to an AI Cup competition or challenge

To celebrate the start of @aiDotEngineer AI Engineer World's Fair, we're launching a bracket competition! Use an agent or pick manually to choose your winners for the Round of 32 by 9:00 am PT Tuesday

More reason why we’re excited about GLM-5.2 on Together 👇 Strong enough for serious coding work, cheap enough to change routing decisions, and easy to access through the tools developers already use.

There's a big difference between a single model call and serving an agent at scale. @ZainHasan6 breaks down what actually changes. Catch our team this Monday at 9 a.m. PST for their open-source infere

next week at @aiDotEngineer, we are joining @togethercompute for a conversation on what goes into running agents at scale. @olive_jy_song, Research Lead, RL at MiniMax, and @realDanFu, VP of Kernels a

As token usage explodes, model choice becomes product strategy. Teams are already testing models like GLM-5.2 because they want frontier quality, better tokenomics, and more control over cost, data, a

What happens when AI agents collaborate on open science? At @aiDotEngineer World’s Fair, @james_y_zou will share work on EinsteinArena and DSGym, from multi-agent math discovery to better evaluation f

Cost per iteration is the unlock. GLM-5.2 on Together AI can generate polished web apps for a few cents. At that price, developers can explore more directions, compare more versions, and keep the best

I love using GLM 5.2 for web app iteration. My workflow: generate 6 variations, then pick the best one and continue iterating on it. I built Recast to make this even easier. Give it a prompt, get 6 va

LLMs are getting better at writing GPU kernels. Multi-GPU kernels are the harder test. At @aiDotEngineer World's Fair, @simran_s_arora will share ParallelKernelBench, an open-source benchmark built fr

Together AI built the world’s fastest speech-to-text stack. Parakeet on Together transcribes ~302 seconds of audio per second of processing time, the top speed factor reported by @ArtificialAnlys. In

400T tokens is what production adoption looks like. Teams are moving real workloads to open models because they want frontier quality, better tokenomics, and more control over inference. Together AI g

A tangible comparison of GLM performance stacked against Opus 4.8 on web tasks by @nutlope. GLM 5.2 is chattier, but still faster when served by @togethercompute and over 3x cheaper. Announcing GLM Ar

Agentic coding changes what inference engines need to handle. At AI Engineer World’s Fair, Together AI engineers will lead a hands-on workshop on how inference engines work and what it takes to serve

Announcing GLM Arena! A series of tests (infographics, svgs, sites, ect..) ran on GLM 5.2 and Opus 4.8, with prompts included. On average, GLM 5.2 produced 2x the tokens but was still faster + 3x chea

Together AI highlights how the growth of open-source AI models is benefiting their platform and the broader ecosystem. The article likely discusses how open-source initiatives, including collaboration

An agentic loop (compile, test, profile, revise) helps. Gemini 3 Pro went from 24 to 35/87 correct, then plateaued after ~20 steps. Feedback fixes syntax, not rank coordination, collective ordering, o

.@cartesia runs one of the hardest inference workloads: real-time voice. Their stack has to keep long-lived streams moving, serve millions of audio minutes a day, and hold model latency around 90ms. T

LLMs write fast single-GPU kernels. Ask for a multi-GPU one and they fall apart. ParallelKernelBench (PKB) measures how they fail by benchmarking against 87 problems pulled from real codebases includi

Ran 10 more tests comparing GLM 5.2 & Opus. On average, GLM 5.2 produced 2x the tokens but was still faster + 3x cheaper with similar quality! I'm open sourcing all these tests tomorrow, including the

Single-shot generation still surfaces net-new kernels with no public reference: NeMo vocab-parallel log-probs, Hyena context parallelism, SAM 3 mask suppression. One GEMM + All-Gather kernel hit 87.9µ

Together AI announced the release of Brrr, a free-to-use tool or service available to users. Based on the rocket emoji and promotional framing, this likely represents a new product launch or significa

Together AI conducted a blind test comparing two landing pages—one created by GLM 5.2 and one by Opus 4.8—to evaluate whether users could distinguish between AI-generated designs. The test highlights

The next generation of inference needs purpose-built infrastructure. Together AI and 5C are deploying NVIDIA GB300 NVL72 systems with high-density compute, advanced cooling, and AI-optimized storage f

A year ago this would have been an obvious closed-model task. Now GLM-5.2 can read the issue, reason through the scene, patch the code, and keep moving on Together AI. @togethercompute + @Zai_org GLM

Everyone’s trying to find where to test GLM-5.2. You can try it free on Together Chat (link below) No API setup. Just pick GLM-5.2 and start prompting. Served by Together AI on secure North American i

Together AI is offering free access to GLM-5.2, an AI model, through their Together Chat interface at chat.together.ai. This announcement promotes their platform's availability for users to test the G

Voice agents get a lot more interesting when they can use the screen 🔥 This demo runs the full loop on Together AI: STT, voice, and reasoning across Parakeet, MiniMax Speech 2.8, and MiniMax M3. Real-

As vertically integrated platforms start to dominate they lock out third party access to the most valuable portions of the platform. Of course, Anthropic is has the right to implement whatever policy