The San Francisco Tensor Company
San Francisco, CA
Joined September 2025
- Tweets19
- Following1
- Followers390
- Likes113
San Francisco Tensor Company retweeted
turns out when you have too many GPUs for your own good you can do stupid stuff such as pre-training a foundation model with constrained decoding on PTX -- that is, it does not speak natural language, it's tokenizer is PTX, it's thoughts are PTX, it's all PTX 🧵
San Francisco Tensor Company retweeted
We're #1 on NVIDIA's SOL-ExecBench across all four tracks.
Across 235 real production kernels run on B200s we beat out 583 teams, including teams that have raised hundreds of millions of dollars to optimize kernels.
Along the way we learned a lot about agentic optimization 🧵
San Francisco Tensor Company retweeted
We've been working on training our own models for large-scale, long-running optimization tasks.
The model is still training, but we asked an early checkpoint to optimize pre-training on 32 MI355x, surprisingly it manages to train faster than NVIDIA NeMo running on 32 GB200s 🧵
San Francisco Tensor Company retweeted
for RL and agents you need fast, isolated sandboxes which is why we've used gVisor for CPU and NVIDIA GPU workloads.
as we started post-training models for AMD GPU kernels though, we hit a problem: gVisor has no AMD GPU support. or rather, it didn't, until we built it :)
San Francisco Tensor Company retweeted
We have Day‑0 support for Xiaomi-Robotics-1 at @SFTensor
Let us help you specialize it for your use case
Xiaomi-Robotics-1 is now open source!🎉
Xiaomi-Robotics-1 was pre-trained on more than 100,000 hours of UMI data and post-trained with over 10,000 hours of cross-embodiment data.
This open-source release covers the complete pipeline from real-robot post-training to model deployment and also includes evaluation code for benchmarks.
🌐Project Page :robotics.xiaomi.com/xiaomi-r…
💻GitHub: github.com/XiaomiRobotics/Xi…
📎Hugging Face: huggingface.co/collections/X…
We will continue exploring the broader possibilities of general-purpose robot models.
#Robotics #EmbodiedAI #FoundationModels #RobotLearning #XiaomiAI #XiaomiRobotics
San Francisco Tensor Company retweeted
The biggest advantage of owning the backend end-to-end is that instead of relying on ptxas, you can try different ways of scheduling, such as search & RL. While ptxas beats our beta backend without search, once we turn on search we beat it by ~8 points 🧵
we've long been dissatisfied with the fact that the closest we can get to the hardware on NVIDIA is PTX, with ptxas then making all sorts of decisions (instruction selection, barriers, stall counts, etc.) for us without any way to influence it, so we've been building a custom LLVM backend that let's us create cubins directly from LLVM, which let's us do things such as write inline SASS and define custom scheduling. reply or reach out if you wanna give it a twirl
San Francisco Tensor Company retweeted
we've long been dissatisfied with the fact that the closest we can get to the hardware on NVIDIA is PTX, with ptxas then making all sorts of decisions (instruction selection, barriers, stall counts, etc.) for us without any way to influence it, so we've been building a custom LLVM backend that let's us create cubins directly from LLVM, which let's us do things such as write inline SASS and define custom scheduling. reply or reach out if you wanna give it a twirl
San Francisco Tensor Company retweeted
The benefits of AI are dangerously concentrated. Today they accrue to a handful of labs and to one industry, software, whose work happens to look like the internet the models were trained on.
Changing that is the single biggest untapped lever for economic growth this decade.🧵
San Francisco Tensor Company retweeted
And because we automatically target whichever hardware is cheapest or best for a given workload, vendors have to compete on performance and price instead of coasting on lock-in.
A chip that becomes uncompetitive can no longer hide behind switching costs. It has to win on the merits.
San Francisco Tensor Company retweeted
We built a software model of NVIDIA Blackwell's Tensor Core MMA instruction (tcgen05.mma) that matches real B200 hardware bit-for-bit.
Not "close enough for numerics." Every output word, identical.
Here's how we reverse-engineered it. 🧵
San Francisco Tensor Company retweeted
We've stopped testing our GPU kernels and started proving them correct instead.
A test suite checks the inputs you thought of. A proof covers every input that exists and hands you the exact one that breaks the kernel if it's wrong.
Here's how. 🧵
San Francisco Tensor Company retweeted
The moment we saw this letter, we signed. An open ecosystem beats a closed moat every time and is how AI actually reaches every sector. Proud to stand with everyone helping build and accelerate open, American AI
Since launching last week, more than 230 companies and organizations from across the tech sector have signed the "Open Weights and American AI Leadership" open letter. We want to thank these partners for standing up and publicly supporting broader access to AI innovation. A special thanks to @nvidia, @a16z, and @PalantirTech for working with @Microsoft on this effort.
These signatories understand that America’s AI leadership will not depend on the success of our frontier models alone, but on our ability to build a strong, secure, and open ecosystem that diffuses AI into every sector. We look forward to continuing to work with our partners and with policymakers to build that open ecosystem in a way that benefits American businesses, empowers American workers, and strengthens the American economy.
San Francisco Tensor Company retweeted
We built a benchmark where the AI agent has to build an inference chip. GPT-5.6 took 3.4 days and 1.7B tokens.
The agent has to design, verify and physically place-and-route a working inference accelerator from a single MAC unit to a routed die that decodes tokens bit-exactly.
made it to Times Square! now back to building
thanks @brexHQ for the support getting here
San Francisco Tensor Company retweeted
San Francisco Tensor Company retweeted
Excited to have powered the training infrastructure for @KalpaLabsAI's latest model.
Congrats to @JhaGauti and @pshishodiaa on the launch and excited to see where you take it!
Kalpa Labs (@KalpaLabsAI) is training one generalist model for all speech tasks. Steer it like an LLM, give long system prompts & make use of native contextual awareness.
Congrats on the launch, @pshishodiaa and @jhagauti!
ycombinator.com/launches/Op4…
San Francisco Tensor Company retweeted
SF Tensor (@sftensor) is building infrastructure for training foundation models, letting researchers focus on research and forget that the infrastructure layer even exists while saving 70% in training costs.
ycombinator.com/launches/Ojq…
Congrats on the launch, @benkoska, @tom_koska, and @lukkoska!
Running AI workloads across clouds is honestly a nightmare. GPU availability is random, prices swing wildly, and managing AWS + GCP + Azure + niche providers is basically a full-time job.
We got sick of it, so we built Elastic Cloud. (1/2)
One interface for everything. Automatically finds cheap GPUs, handles spot instances (saves up to 80%), moves jobs around when needed.
Tell us what you need. Your training runs. That's it.
cloud.sf-tensor.com