Register and share your invite link to earn from video plays and referrals.

Search results for 284
284 community
One keyword maps to one global community path.
Create community
People
Not Found
Tweets including 284
TensorFold 1.3.3 is out 🚀 124 PR's merged and 34 Issues resolved in 24h GLM-5.3-Flash went from 151.51 to 172.39 tok/s in median drafted decode after a 1,040,384-token prompt on four GB10s at TP=4. That’s 13.8% faster on CUDA with the same output tokens in that test. Thanks to @MiaAI_lab for the kernel behind that gain. - On Metal, GLM-5.3-Flash gets DFlash2 drafting. On a Mac without tensor units, GLM cold prompts from 2K to 64K took about 5–6% less time in the release tests. - MOSS-Image generates pictures on CUDA through /v1/images/generations. GLM-OCR runs on HIP, and Idol gets its image encoder on Metal. - DeepSeek-V4.1 gets structured output in the dsv41-cuda source build. Long CUDA prompts now prefill in chunks alongside running replies by default. - LFM2-MoE, LFM3, MiniMax-M3 and Qwen3.5-2B on Metal can fill new prompts between other streams’ decode rounds. - The server adds per-request deadlines, a prompt-cache flush endpoint, and deferred and namespaced tools. Massive thanks to everyone who sent patches, tested on their own hardware, and filed repros. @AIFlow_ML @bikepresentball @Bizuayeu @devopsfortunato @unigilby @javierbits @jayleaton @teleogen @niklaslenz_ai @plotarmordev @woolsey @petruspennanen @andersjw_ @shantanugoel @dennis_rye, and on GitHub AbrahamCete, BadAd84, Ch0mpaa, christopherowen, CodingEmil, eXsoR65, Flyinpiz-dev, garvrao80, hobbesd, jschmied, kotevcode, MaverickKB, millaguie, nuk3s, SergiioB, supernovae, tacosta and ultradaoto. I really appreciate the time you put into this. @plotarmordev @jayleaton @petruspennanen @MiaAI_lab @volatilemarkts
Show more
What’s the best value vs quantity mic for video calls and pod casts etc? Looking at the @Razer Mini V3.
Unbelievable, building open source and getting paid by X to do it. Everything goes back into my open source work. Thank you ❤️🙏
TensorFold 1.3.2 is out 🚀 96 merged PRs in this release and 31 issues closed since 1.3.0. A lot of that came from people sending patches, trying builds on their own hardware and coming back with an actual repro when something broke. Thank you. - DeepSeek-V4.1 now takes images on Metal. Decode was 6–17% faster at one and two streams on an M5 Ultra, with the same tokens in that test. - Hy4-flash on Metal is included. dots.mocr now takes images on CUDA, and the OCR endpoint reads PDFs on HIP. - Muse Spark Open runs on two GB10s, and Qwen3.8 Flash Next runs with MTP and prompt snapshots on Intel Xe2. - Idol’s octree and Gaussian decoders now run natively on M5 Metal. - tensorfold chat streams replies in your terminal, tensorfold log shows request timings, and you can pull gated Hugging Face models. Massive thanks to @AIFlow_ML @andersjw_ @bikepresentball @Bizuayeu @devopsfortunato @unigilby @GumbiiDigital @javierbits @jayleaton @joshuaswarren @teleogen @niklaslenz_ai @plotarmordev @shantanugoel @Shoestring_Dev @arthurostapenko, and on GitHub BadAd84, BobClawblaw, davidzogg13-boop, ElderOrb, hobbesd, jamesadcock, jschmied, SergiioB, supernovae, trickyfalcon, ultradaoto, yguanrong and ercumentyildirim. I really appreciate the time you all put into this. @plotarmordev @jayleaton @MiaAI_lab @volatilemarkts @petruspennanen
Show more
My main goal with AI is to enrich people’s lives through technology, and that’s why I’m building NearDAR. I want it to be an extra pair of eyes you can call on when you want more information about what’s around you. Ask a question, hear what the camera can pick up, and decide what to do next on your own terms. Walk into a café you’ve never been to and ask which seats look free. Pick up an item at the supermarket and check it’s the one you came for. Find where the checkout queue starts. The prototype can already take a camera view and speak an answer offline. I’m working toward the TensorFold Mobile engine running fully locally on your phone, Ray-Ban Meta glasses as a hands-free camera, and a gentle tap when you’re facing what you’re looking for. NearDAR will be free and open source. If you know someone who’s blind or has low vision, please share this with them. I’d love to hear directly from the people I’m building NearDAR for. @cerebras @zhennydez @Kimi_Moonshot, this is one of the things I am using the Cerebras Kimi K3.1 Pro for. powered by @tensorfold_dev
Show more
TensorFold 1.3.0 is out 🚀 GLM-5.3-Flash went from 83.8 to 104.1 tok/s on two RTX PRO 6000 Blackwells. That’s about 24% faster on CUDA at TP=2 with NVFP4 experts, drafts off and the same output bits in that test. - On Metal, DeepSeek-V4.1’s prompt-attention kernel is about 1.5× faster, and GLM-5.3-Flash follow-ups reach the first token 3–4% sooner. - On CUDA, Flash Next frees about 3 GiB of page cache after loading the NVFP4 export. On Linux, you can opt in to mapping KV pages as streams need them. - tensorfold models now show which chat checkpoints fit your machine. On Metal, tensorfold info accounts for context and parallel streams when estimating memory for Qwen3.8-27B-class models. - Idol’s denoiser runs natively on Metal and on supported NVIDIA Blackwell GPUs. - The server has opt-in JSON request logs and a journal for replaying requests after a crash. Stored Responses are scoped to the API key that created them. - Desktop now loads Qwen3.8-27B correctly from the model library, and TensorFold Web accepts OpenAI-compatible base URLs ending in /v1. Massive thanks to everyone writing code, testing it on their hardware and filing bugs. @AIFlow_ML @andersjw_ @arminxnova @atasrb @Bizuayeu @codengod @devopsfortunato @Eleqtrizit @unigilby @GumbiiDigital @jayleaton @teleogen @lasse_ai @mvanhorn @niklaslenz_ai @petruspennanen, and on GitHub AbrahamCete, BadAd84, jschmied, mrv777, supernovae, ultradaoto, vdalesandro, terrapinelf and Mirrdhyn. I really appreciate the time you all put into this. @petruspennanen @plotarmordev @volatilemarkts @MiaAI_lab @jayleaton
Show more
TensorFold 1.2.10 is out 🚀 Qwen3.8-27B decodes 57% faster on a GB10 at 8 streams with a shared 32K prefix, with the same replies in that test. DeepSeek-V4.1 cold prompts are 5–7% faster on an M5 Ultra. We also shipped background responses, tensorfold launch and tensorfold rm, plus Qwen3-Embedding and Unlimited-OCR-2 on Metal. Additionally squashed a few bugs and issues. Massive thanks to everyone who wrote code, ran tests on their hardware and reported bugs. @AIFlow_ML @Bizuayeu @codengod @devopsfortunato @EugineAi @unigilby @jayleaton @teleogen @niklaslenz_ai @plotarmordev @woolsey @petruspennanen, and on GitHub AbrahamCete, akol1, BadAd84, BobClawblaw, currencycaver29, cwschroeder, dinadur, drowzeys, garvrao80, ilya-bogin-keenable, jschmied, Mirrdhyn, robertosantosx2, srh3877, sx4im and tacosta. I really appreciate the time you all put into this. @petruspennanen @volatilemarkts @MiaAI_lab @plotarmordev @jayleaton @tensorfold_dev
Show more
TensorFold 1.2.10 is out 🚀 Qwen3.8-27B decodes 57% faster on a GB10 at 8 streams with a shared 32K prefix, with the same replies in that test. DeepSeek-V4.1 cold prompts are 5–7% faster on an M5 Ultra. We also shipped background responses, tensorfold launch and tensorfold rm, plus Qwen3-Embedding and Unlimited-OCR-2 on Metal. Additionally squashed a few bugs and issues. Massive thanks to everyone who wrote code, ran tests on their hardware and reported bugs. @AIFlow_ML @Bizuayeu @codengod @devopsfortunato @EugineAi @unigilby @jayleaton @teleogen @niklaslenz_ai @plotarmordev @woolsey @petruspennanen, and on GitHub AbrahamCete, akol1, BadAd84, BobClawblaw, currencycaver29, cwschroeder, dinadur, drowzeys, garvrao80, ilya-bogin-keenable, jschmied, Mirrdhyn, robertosantosx2, srh3877, sx4im and tacosta. I really appreciate the time you all put into this. @petruspennanen @volatilemarkts @MiaAI_lab @plotarmordev @jayleaton @tensorfold_dev
Show more
We now have a recipe catalog on our website with deployable containers ready to go. @tensorfold_dev