tensorfold
tensorfold is LLM Inference Engine for Metal, CUDA and Vulkan. Contribute to hikarioyama/TensorFold development by creating an account on GitHub.. It is ranked #1613 on the Dev Radar, in AI dev tools, first seen 19 days ago and shared in 6 posts (53.3k views).
GitHub - hikarioyama/TensorFold: LLM Inference Engine for Metal, CUDA and Vulkan. · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation TensorFold Public forked from ashhart / TensorFold Notifications You must be signed in to change notification settings Fork 0 ( 0 ) Star 8 ( 8 ) You must be signed in to star…
What people said about tensorfold on X
Optimized TensorFold for GLM5.3 EXL3 and achieved 87-95 tok/s on 4x RTX PRO 6000! Speculative decoding is MTP. Uncensored SOTA models at home are starting to become a reality🔥 https://github.com/hikarioyama/TensorFold
— @Hikari_07_jp, 19 days ago · 206 likes · see the post
GLM 5.3の推論を改善し続けています。 「43k tokenのPythonコードを読ませて実装上のリスクを指摘する」というタスクにおいてデコード速度が60tok/sから72tok/sに改善しました！！ 実際にエージェントとして使う想定で20%の速度向上です。 さて、TensorFoldやStrataを知っている皆さんはご存知だと思いますが、推論最適化は未解決の問題です。手元にあるハードウエアの働きは推論最適化によって大きく変化します。世界中の開発者が計算資源を買ってトークンと時間を注ぎ込みオープンソースで最適化を続けるアツい分野です。 私はNVIDIAの最新GPU環境向けの最適化をやっていきたいと思っています。GLM…
— @Hikari_07_jp, 18 days ago · 106 likes · see the post
The full GLM 5.3 EXL3 hitting ~95tp/s decode 🤯🤯🤯🤯🤯
— @ashxhart, 19 days ago · 90 likes · see the post
Alternatives to tensorfold
- goo.gle — Officially in beta, the AppFunctions API is opening up powerful new ways to integrate your functionality.
- Kimi AI with K3.1 Pro — Try Kimi K3.1 Pro to tackle complex coding projects, build 3D models, conduct financial research, and take on more…
- Agents in flight — Give it a try
- Baseten — This session is our most in-demand yet. See you there
- project-maya — Checkout Maya
- deepinfer — You gotta love Deepseek. This is awesome stuff!
tensorfold in numbers
- Rank on the Dev Radar: #1613 of 8801
- Shared in 6 posts by 3 accounts: @Hikari_07_jp, @ashxhart, @u1tra_instinct
- 53.3k views on those posts
- First seen 19 days ago, last shared 18 days ago
- Pricing seen by AGK Intelligence: open source
- Market: AI dev tools
FAQ
What is tensorfold?
LLM Inference Engine for Metal, CUDA and Vulkan. Contribute to hikarioyama/TensorFold development by creating an account on GitHub. It was first shared on X 19 days ago and is ranked #1613 on the Dev Radar.
Is tensorfold free?
It is open source.
Who shared tensorfold?
3 accounts on X, including @Hikari_07_jp, @ashxhart, @u1tra_instinct, in 6 posts totalling 53.3k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 21:12 UTC. Full method.