I improved NanoGPT Speedrun from 39.9s → 6.7s (-83.2%), more than every record since 2025 combined (-81.4%)! The web is full of rare, repeated content that the LM can’t memorize in time. I solve this with retrieval-augmented n-gram hints🧵 https://t.co/PKQdSpWdxP

We wrote a 37-page technical report on OCRia-1, our SOTA model for document parsing. ✅ It contains comprehensive evals against most other major open-weight OCR models (e.g. Infinity-Parser, LightOnOCR 3, Chandra 2, dots.mocr) on multiple OCR benchmarks: ParseBench, olmOCR-bench, PulseBench-Tab, fr-bench-pdf2md. ✅ It contains detailed visibility into our data and training pipeline, to give a glimpse into how we’re able to curate the right document datasets to push the evaluation metrics within dimensions that matter for doc parsing. ✅ It is blazing fast ⚡️ decoding 2x-4x+ faster than the latest open-weight models. ✅ If you’re building your own vision models, there are 24 pages worth of appendix details (!!) that showcase all of our experimental findings from training to evals! Check it out: https://t.co/DX1bSISNP1 Other links are in our blog! https://t.co/PRxvOFmlVH

We wrote a 37-page technical report on OCRia-1, our SOTA model for document parsing. ✅ It contains comprehensive evals against most other major open-weight OCR models (e.g. Infinity-Parser, LightOnOCR 3, Chandra 2, dots.mocr) on multiple OCR benchmarks: ParseBench, olmOCR-bench, PulseBench-Tab, fr-bench-pdf2md. ✅ It contains detailed visibility into our data and training pipeline, to give a glimpse into how we’re able to curate the right document datasets to push the evaluation metrics within dimensions that matter for doc parsing. ✅ It is blazing fast ⚡️ decoding 2x-4x+ faster than the latest open-weight models. ✅ If you’re building your own vision models, there are 24 pages worth of appendix details (!!) that showcase all of our experimental findings from training to evals! Check it out: https://t.co/DX1bSISNP1 Other links are in our blog! https://t.co/PRxvOFmlVH

vLLM 🤝 TPU 🚀 Native PyTorch serving on TPUs is here! Built with @Google and @inferact, vLLM-TorchTPU brings familiar PyTorch tools to TPU inference, with prefix caching, speculative decoding, and disaggregated serving. 🛠️ Excited to keep building with the community!

llama.cpp b11938 on M2 Pro 32 GiB (using ~3 GiB with the full 128K context) at ~110 t/s with c1 running with Pi! llama serve --hf-repo LiquidAI/LFM3-VL-2B-GGUF:Q4_K_M --host 0.0.0.0 --port 8080 -fa on -np 1 --top-p 1.0 --min-p 0.0 https://t.co/enITzfYaPQ

Bill Jia (@GoogleCloud) and Zongwei Zhou (@Meta) introduce TorchTPU, a native PyTorch backend for Google TPUs, and agentic developer workflows at #PyTorchCon 2026. TorchTPU is an open source collaboration between Google and Meta, developed in close partnership with PyTorch core maintainers. It integrates with Hugging Face Transformers for modeling, TorchTitan for training, and vLLM and SGLang for serving. They demonstrate how long-horizon agentic workflows can migrate complex model workloads from GPUs to TPUs. They explore using agents for performance optimization, including quantization, custom kernel generation, and advanced sharding strategies. Watch the keynote livestream: https://t.co/6TtaEkvsHz

If you're using LoRA for RL, it's most likely best to deploy your adapter unmerged. Depending on your learning rate, how many effective train steps, etc, you might be losing much of your training updates to rounding to BF16 when you merge the adapter to the base model. https://t.co/xnqBTHVzOW

@googlecloud @Meta Read our latest blog introducing TorchTPU to learn more: https://t.co/WnaK5hLFBd

MacVoice Full voice loop on a MacBook, running on a local LLM - Just talk over the agent to interrupt it. First spoken word of the reply arrives **~0.7 s after you stop talking**. Fits in **1.4 GB**. No PyTorch. Writeup + repo 👇 https://t.co/nfKHKeawK6 https://t.co/UIa6WvXcM2 🔊 Sound on.

+1 more

In Axolotl, we’ve addressed this with merge-aware LoRA training: we merge the LoRA into the base weights and cast to BF16 inside the forward pass, so the model trains on exactly the weights vLLM serves. Gradients pass straight through the rounding to the LoRA weights, so they keep learning even when a single step is too small to change a BF16 weight. While there are still gaps in this method (support for various distributed parallelisms, ZeRO-3, etc), we hope we can help ensure that you aren't left wondering why what you deployed is underperforming.