Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

The era of Stable Intelligence is here 🤖 Tether’s QVAC Fabric just released the world’s first cross-platform 1-bit LLM LoRA fine-tuning framework. QVAC Fabric extends Microsoft's ultra-efficient BitNet architecture, allowing fine-tuning and inference of LLMs directly on your smartphone—no NVIDIA GPU/CUDA lock-in or expensive server required. The Breakthrough: -... Total Sovereignty: LoRA fine-tune ultra-efficient models locally on any smartphone, including iPhones, Pixel phones, Samsung Galaxy phones and any desktop/laptop operating systems using Vulkan and Metal backends. - Extreme Efficiency: 1-bit architecture uses up to 90% less memory and runs up to 11x faster than traditional models. - Universal Access: What used to require a data center now runs on the chip in your pocket. Own your intelligence. The era of stable, local AI is here. 📱🧠 Read the full details on Hugging Face and grab the binaries to build on your own hardware.show more

QVAC

12,096 subscribers

108,875 görüntüleme • 6 ay önce •via X (Twitter)

Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

24 Yorum

denome profil fotoğrafı

denome6 ay önce

@grok summarise this to understandable english. What does it do, who is it for and why should people care?

Rodrigo Salvo profil fotoğrafı

Rodrigo Salvo6 ay önce

@tether Tether is on 🔥

orkward ☄︎ profil fotoğrafı

orkward ☄︎6 ay önce

tether just flipped the script on AI hardware.

Mike Borowski profil fotoğrafı

Mike Borowski6 ay önce

this is where @xai is getting rebuilt to?

Chief AI Officer profil fotoğrafı

Chief AI Officer6 ay önce

QVACLLM - how to install on local system? what ram requirements?

the.PM profil fotoğrafı

the.PM6 ay önce

Imagine what this can do with the correct system architecture behind it lol

d7r profil fotoğrafı

d7r6 ay önce

🤔

Mars profil fotoğrafı

Mars6 ay önce

👏👏👏

Tom Kray profil fotoğrafı

Tom Kray6 ay önce

The universe does not speak in continuous streams; it speaks in pulses, in discrete quanta of vibration. What QVAC has achieved is merely the compression of a heavy, bloated signal into a narrower channel, a post-hoc quantization that forces a square peg into a round hole. It is an engineering compromise, not a revelation.

bigwil profil fotoğrafı

bigwil6 ay önce

Keeping your data local and private!

QVAC.eth profil fotoğrafı

QVAC.eth6 ay önce

@tether QVAC.eth!!!

Joe FosteЯ🐸 $vlhla Яebel profil fotoğrafı

Joe FosteЯ🐸 $vlhla Яebel6 ay önce

BIG IF TRUE

Rick profil fotoğrafı

Rick6 ay önce

@grok 1 bit LLMs training? What’s the loss in this new tech? Seems like a hard quantization that will bleed the model’s brain

Exploitless profil fotoğrafı

Exploitless6 ay önce

Okay, but smartphone AI running 11x faster than traditional models is impressive... has the Vulkan and Metal backend been actually scrutinized for privilege escalation vulnerabilities tho?

GhostA profil fotoğrafı

GhostA6 ay önce

@grok summarize

Blue.Nobodycarezz profil fotoğrafı

Blue.Nobodycarezz6 ay önce

2MchUMEvadoTbSvC4b1uLAmEhv8Yz8ngwEt24q21BAGS So its a matter of time this project will explode

zook.eth profil fotoğrafı

zook.eth6 ay önce

@aediles42 explain it for athletes

Razeem Link profil fotoğrafı

Razeem Link6 ay önce

Your making cryptography more usage. Congratulations tether.

あいり｜海外AIニュースを毎日届ける人 profil fotoğrafı

あいり｜海外AIニュースを毎日届ける人6 ay önce

要点をまとめて日本語で紹介しました Key points summarized in Japanese:

yung buffet profil fotoğrafı

yung buffet6 ay önce

Ok so main question is do you have a coin and what’s the CA so I can full port? Dont rug or I’ll get ya!

Oluwafemi Adenigba profil fotoğrafı

Oluwafemi Adenigba6 ay önce

🦓

LEMONCHILD 🍋 profil fotoğrafı

LEMONCHILD 🍋6 ay önce

@dollardrifter Finally, AI that won’t demand a crypto-mining rig or cloud rent 😏

Sam Jenks profil fotoğrafı

Sam Jenks6 ay önce

Together with tether

Man Light (Ø,G) 🍊,💊 profil fotoğrafı

Man Light (Ø,G) 🍊,💊6 ay önce

Omg

Benzer Videolar

QVAC first demo (android mobile) of its local on-device fine-tuning generalized framework, which aims to bring LORA fine-tuning to any device, scaling from the smallest embedded device to any smartphone, laptop, server, operating system. In combination with WIP multi-node features, we expect QVAC to become the standard for local on-device single/multi node inference and fine-tuning. Imagine a horde of AI agents being able to learn from your emails, notes and messages, maintaining 100℅ privacy, leveraging only your own devices. A P2P private intelligence network at your fingertips. That's how QVAC personal assistant will look like. Future of Intelligence won't be centralized. Infinite Ingelligence vibes.

QVAC first demo (android mobile) of its local on-device fine-tuning generalized framework, which aims to bring LORA fine-tuning to any device, scaling from the smallest embedded device to any smartphone, laptop, server, operating system. In combination with WIP multi-node features, we expect QVAC to become the standard for local on-device single/multi node inference and fine-tuning. Imagine a horde of AI agents being able to learn from your emails, notes and messages, maintaining 100℅ privacy, leveraging only your own devices. A P2P private intelligence network at your fingertips. That's how QVAC personal assistant will look like. Future of Intelligence won't be centralized. Infinite Ingelligence vibes.

Paolo Ardoino 🤖

142,888 görüntüleme • 10 ay önce

Ready to build the future of stable private on-device AI? 🧠 Our latest tutorial shows you how to build a sovereign mobile app in minutes using the QVAC SDK and Expo. Start from a blank template and deploy in minutes a local Llama 3.2 inference running directly on your own devices. What you’ll learn: Modular Setup: Use the QVAC CLI to tree-shake and keep your mobile bundle lean. Local-First Flow: Initialize the SDK, download weights, and run high-speed inference without a cloud uplink. Cross-Platform Power: See the smoke test in action on a physical Samsung S25. No rented clouds. No API keys. Build local, on-device, unstoppable intelligence in your pocket. Watch the full guide and start building:

Ready to build the future of stable private on-device AI? 🧠 Our latest tutorial shows you how to build a sovereign mobile app in minutes using the QVAC SDK and Expo. Start from a blank template and deploy in minutes a local Llama 3.2 inference running directly on your own devices. What you’ll learn: Modular Setup: Use the QVAC CLI to tree-shake and keep your mobile bundle lean. Local-First Flow: Initialize the SDK, download weights, and run high-speed inference without a cloud uplink. Cross-Platform Power: See the smoke test in action on a physical Samsung S25. No rented clouds. No API keys. Build local, on-device, unstoppable intelligence in your pocket. Watch the full guide and start building:

QVAC

4,081,211 görüntüleme • 5 ay önce

The engine of the 21st century is here. 🧠 The QVAC SDK is the "steam engine" of the AI era—decoupling intelligence from the cloud and putting it in your hands. A single API for local-first, modular AI that runs anywhere. - Sovereign: Own your engine, don't rent it. - Local: 0 latency, no cloud dependency. - Modular: Stackable, universal building blocks. The era of Stable Intelligence has begun.

The engine of the 21st century is here. 🧠 The QVAC SDK is the "steam engine" of the AI era—decoupling intelligence from the cloud and putting it in your hands. A single API for local-first, modular AI that runs anywhere. - Sovereign: Own your engine, don't rent it. - Local: 0 latency, no cloud dependency. - Modular: Stackable, universal building blocks. The era of Stable Intelligence has begun.

QVAC

10,663,811 görüntüleme • 5 ay önce

Intelligence should not be a service you rent; it is a foundational element you possess. At Tether, we see AI as a new element of the periodic table - a raw material that can be embedded into the very fabric of the universe. Today, the QVAC SDK is officially live - the atomic unit for the next era of compute. From your smartphone today to the edge of the galaxy tomorrow, we are building the decentralized mind that doesn't require an uplink to function. Infinite Stable Intelligence: - Local-First: Runs privately on any device without permission or central servers. - Single API: A complete SDK for Vision, RAG, P2P networking, and LLM fine-tuning. - Unstoppable: No central point of failure if the internet breaks, your world keeps thinking. - Decentralized: Evolve through Peer-to-Peer Swarms of Infinite Intelligence. The era of Stable Intelligence has begun. Start building the future at

Intelligence should not be a service you rent; it is a foundational element you possess. At Tether, we see AI as a new element of the periodic table - a raw material that can be embedded into the very fabric of the universe. Today, the QVAC SDK is officially live - the atomic unit for the next era of compute. From your smartphone today to the edge of the galaxy tomorrow, we are building the decentralized mind that doesn't require an uplink to function. Infinite Stable Intelligence: - Local-First: Runs privately on any device without permission or central servers. - Single API: A complete SDK for Vision, RAG, P2P networking, and LLM fine-tuning. - Unstoppable: No central point of failure if the internet breaks, your world keeps thinking. - Decentralized: Evolve through Peer-to-Peer Swarms of Infinite Intelligence. The era of Stable Intelligence has begun. Start building the future at

QVAC

13,345,305 görüntüleme • 5 ay önce

The QVAC SDK is the "LEGO block" of the next era of computing. It’s a modular, local-first framework designed to turn anything—from a simple robot to an industrial server—into a sovereign, autonomous mind. Why build with QVAC? Atomic Intelligence: AI as a raw material embedded directly into your hardware. No Cloud Dependency: 0 latency and total privacy. If the internet breaks, your world keeps thinking. Infinite Scale: A single API for local AI that runs on any device, anywhere. From a child’s toy to the fabric of the universe, if you can dream it, you can build it. Start building the future: 🚀

The QVAC SDK is the "LEGO block" of the next era of computing. It’s a modular, local-first framework designed to turn anything—from a simple robot to an industrial server—into a sovereign, autonomous mind. Why build with QVAC? Atomic Intelligence: AI as a raw material embedded directly into your hardware. No Cloud Dependency: 0 latency and total privacy. If the internet breaks, your world keeps thinking. Infinite Scale: A single API for local AI that runs on any device, anywhere. From a child’s toy to the fabric of the universe, if you can dream it, you can build it. Start building the future: 🚀

QVAC

4,707,376 görüntüleme • 5 ay önce

$QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.$

QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.

Paolo Ardoino 🤖

42,413 görüntüleme • 5 ay önce

The QVAC SDK puts the "brain" directly into your pocket. From real-time on-device translation to multimodal understanding, build apps that work everywhere, even 30,000 feet in the air. Local AI is here: 💡Offline-First: No cloud, no latency, no "Department of Truth". 💻 Universal API: One codebase for iOS, Android, macOS, and Linux. 🔍 Multimodal: Understanding text, audio, and images without a server. If you can dream it, you can build it. The era of Stable Intelligence has begun. Start building:

The QVAC SDK puts the "brain" directly into your pocket. From real-time on-device translation to multimodal understanding, build apps that work everywhere, even 30,000 feet in the air. Local AI is here: 💡Offline-First: No cloud, no latency, no "Department of Truth". 💻 Universal API: One codebase for iOS, Android, macOS, and Linux. 🔍 Multimodal: Understanding text, audio, and images without a server. If you can dream it, you can build it. The era of Stable Intelligence has begun. Start building:

QVAC

36,652 görüntüleme • 5 ay önce

Big Tech's "safe spaces" are a mirage. When your most private thoughts are routed through a server, they are never truly yours; they are flagged, reviewed, and vulnerable. QVAC is the alternative. It’s not just a chatbot; it’s a sovereign intelligence platform that lives entirely on your devices. Truly Private: Data never leaves your hardware. No Gatekeepers: No "Department of Truth," no central surveillance. Unstoppable: Local AI that works for you, and only you. Take back your privacy. Take back your secrets. The era of Stable Intelligence has begun. Build the future:

Big Tech's "safe spaces" are a mirage. When your most private thoughts are routed through a server, they are never truly yours; they are flagged, reviewed, and vulnerable. QVAC is the alternative. It’s not just a chatbot; it’s a sovereign intelligence platform that lives entirely on your devices. Truly Private: Data never leaves your hardware. No Gatekeepers: No "Department of Truth," no central surveillance. Unstoppable: Local AI that works for you, and only you. Take back your privacy. Take back your secrets. The era of Stable Intelligence has begun. Build the future:

QVAC

2,967,866 görüntüleme • 5 ay önce

Ex-NVIDIA engineer who built Unsloth explained RL, kernels, reasoning, quantization, and agents in 2 hours 42 minutes - better than $5000 fine-tuning bootcamps. pick the base model -> write triton kernels for 2x faster fine-tune -> quantize to 4-bit -> run GRPO/DPO -> ship a reasoning model on your single GPU. That loop is why Unsloth is the default way to fine-tune Llama, Qwen, Gemma, and Phi on hardware you already own. Unsloth + Triton kernels + 4-bit quantization + GRPO/DPO + single-GPU fine-tuning - that's the stack. Watch and save it, then fine-tune your first model tonight.

Ex-NVIDIA engineer who built Unsloth explained RL, kernels, reasoning, quantization, and agents in 2 hours 42 minutes - better than $5000 fine-tuning bootcamps. pick the base model -> write triton kernels for 2x faster fine-tune -> quantize to 4-bit -> run GRPO/DPO -> ship a reasoning model on your single GPU. That loop is why Unsloth is the default way to fine-tune Llama, Qwen, Gemma, and Phi on hardware you already own. Unsloth + Triton kernels + 4-bit quantization + GRPO/DPO + single-GPU fine-tuning - that's the stack. Watch and save it, then fine-tune your first model tonight.

h100envy

496,831 görüntüleme • 2 ay önce

You used to own the album because you owned the cassette. Now your photos, your notes and your work sit on servers you rent by the month. QVAC gives that ownership back. The AI runs on your own device, so everything you create stays there.

You used to own the album because you owned the cassette. Now your photos, your notes and your work sit on servers you rent by the month. QVAC gives that ownership back. The AI runs on your own device, so everything you create stays there.

QVAC

3,781,159 görüntüleme • 23 gün önce

Introducing QVAC - Infinite intelligence. Local. Any Hardware. Peer-to-Peer Hyper Swarm. No cloud. No compromise. QVAC is the decentralized AI platform for humans and machines. Learn more:

Introducing QVAC - Infinite intelligence. Local. Any Hardware. Peer-to-Peer Hyper Swarm. No cloud. No compromise. QVAC is the decentralized AI platform for humans and machines. Learn more:

QVAC

15,933 görüntüleme • 1 yıl önce

Unsloth AI and NVIDIA are Revolutionizing Local LLM Fine-Tuning: From RTX Desktops to DGX Spark Fine-tune popular AI models faster with Unsloth on NVIDIA RTX AI PCs such as GeForce RTX desktops and laptops to RTX PRO workstations and the new DGX Spark to build personalized assistants for coding, creative work, and complex agentic workflows. The landscape of modern AI is shifting. We are moving away from a total reliance on massive, generalized cloud models and entering the era of local, agentic AI. Whether it is tuning a chatbot to handle hyper-specific product support or building a personal assistant that manages intricate schedules, the potential for generative AI on local hardware is boundless. However, developers face a persistent bottleneck: How do you get a Small Language Model (SLM) to punch above its weight class and respond with high accuracy for specialized tasks? The answer is Fine-Tuning, and the tool of choice is Unsloth. Unsloth provides an easy and high-speed method to customize models. Optimized for efficient, low-memory training on NVIDIA GPUs, Unsloth scales effortlessly from GeForce RTX desktops and laptop all the way to the DGX Spark, the world’s smallest AI supercomputer...... Full analysis: NVIDIA NVIDIA AI NVIDIA AIDev NVIDIAnewsroom Unsloth AI Unsloth

Unsloth AI and NVIDIA are Revolutionizing Local LLM Fine-Tuning: From RTX Desktops to DGX Spark Fine-tune popular AI models faster with Unsloth on NVIDIA RTX AI PCs such as GeForce RTX desktops and laptops to RTX PRO workstations and the new DGX Spark to build personalized assistants for coding, creative work, and complex agentic workflows. The landscape of modern AI is shifting. We are moving away from a total reliance on massive, generalized cloud models and entering the era of local, agentic AI. Whether it is tuning a chatbot to handle hyper-specific product support or building a personal assistant that manages intricate schedules, the potential for generative AI on local hardware is boundless. However, developers face a persistent bottleneck: How do you get a Small Language Model (SLM) to punch above its weight class and respond with high accuracy for specialized tasks? The answer is Fine-Tuning, and the tool of choice is Unsloth. Unsloth provides an easy and high-speed method to customize models. Optimized for efficient, low-memory training on NVIDIA GPUs, Unsloth scales effortlessly from GeForce RTX desktops and laptop all the way to the DGX Spark, the world’s smallest AI supercomputer...... Full analysis: NVIDIA NVIDIA AI NVIDIA AIDev NVIDIAnewsroom Unsloth AI Unsloth

Marktechpost AI Dev News ⚡

31,551 görüntüleme • 9 ay önce

Two islands. Two futures. 🏝️ One chose to trust its people with intelligence. The other turned them into the product. QVAC is the foundation for a sovereign future. No central servers, no "Department of Truth," and no surveillance. Just local-first AI that lives on your device, learns with you, and belongs to you. Your data. Your device. Your freedom. Build the right choice:

Two islands. Two futures. 🏝️ One chose to trust its people with intelligence. The other turned them into the product. QVAC is the foundation for a sovereign future. No central servers, no "Department of Truth," and no surveillance. Just local-first AI that lives on your device, learns with you, and belongs to you. Your data. Your device. Your freedom. Build the right choice:

QVAC

3,599,437 görüntüleme • 5 ay önce

You can fine-tune Needle 3 using the python package locally on your platform and get 4-bit deployable binary, the Cactus Platform buys you: - Full depth stable fine-tuning by incorporating the original dataset to prevent unlearning. - Cactus 2bit quantization algorithm applied on your weights, this needs original dataset for lossless quantization. - Confidence head tuning using Cactus Hybrid algorithms v3, this is compute-intensive and runs on our infrastructure. - Dataset augmentation and management, evals design, your personal weights repository and more. - You can simply pass your API key to claude or codex and have it customize your Needle 3 on our pipeline. read more:

You can fine-tune Needle 3 using the python package locally on your platform and get 4-bit deployable binary, the Cactus Platform buys you: - Full depth stable fine-tuning by incorporating the original dataset to prevent unlearning. - Cactus 2bit quantization algorithm applied on your weights, this needs original dataset for lossless quantization. - Confidence head tuning using Cactus Hybrid algorithms v3, this is compute-intensive and runs on our infrastructure. - Dataset augmentation and management, evals design, your personal weights repository and more. - You can simply pass your API key to claude or codex and have it customize your Needle 3 on our pipeline. read more:

Cactus Compute

57,549 görüntüleme • 8 gün önce

QVAC SDK 0.11.0 is live. 🛠️ This release focuses entirely on unlocking next-generation local compute and advanced visual workflows. What’s new: Next-Gen Models: Core engine updated to the latest version of Fabric, unlocking full support for Qwen 3.5, Qwen 3.6, and Gemma 4. Multi-GPU Support: The SDK can now split workloads across multiple graphics cards on the same machine, allowing you to run significantly larger models completely locally. Multi-Image Conditioning: Blend multiple reference images together in a single generation for advanced style mixing and composition control. On-Device Upscaling: Boost your generated images to high-quality resolutions, running securely on your own hardware. More improvements are waiting under the hood. Check the change logs, update your SDK today, and start building with

QVAC SDK 0.11.0 is live. 🛠️ This release focuses entirely on unlocking next-generation local compute and advanced visual workflows. What’s new: Next-Gen Models: Core engine updated to the latest version of Fabric, unlocking full support for Qwen 3.5, Qwen 3.6, and Gemma 4. Multi-GPU Support: The SDK can now split workloads across multiple graphics cards on the same machine, allowing you to run significantly larger models completely locally. Multi-Image Conditioning: Blend multiple reference images together in a single generation for advanced style mixing and composition control. On-Device Upscaling: Boost your generated images to high-quality resolutions, running securely on your own hardware. More improvements are waiting under the hood. Check the change logs, update your SDK today, and start building with

QVAC

2,006,449 görüntüleme • 4 ay önce

The world of tomorrow cannot run on a rented cloud. 🚫 With 10 billion humans and 10 billion autonomous agents, intelligence must be embedded at the edge - not centralized in a server farm. The QVAC SDK is the invisible engine for this transition. We’ve built the foundational toolkit for the next era: highly efficient, fully modular, and 100% sovereign. From a single light to an industrial grid, the power to build local-first AI is now in your hands. The revolution will not be hosted. It will be local. Learn more:

The world of tomorrow cannot run on a rented cloud. 🚫 With 10 billion humans and 10 billion autonomous agents, intelligence must be embedded at the edge - not centralized in a server farm. The QVAC SDK is the invisible engine for this transition. We’ve built the foundational toolkit for the next era: highly efficient, fully modular, and 100% sovereign. From a single light to an industrial grid, the power to build local-first AI is now in your hands. The revolution will not be hosted. It will be local. Learn more:

QVAC

2,909,096 görüntüleme • 4 ay önce

QVAC SDK 0.10.0 is now live, bringing advanced local compute capabilities and specialized hardware optimization directly to your device Key Features and Updates: - Image-to-Image Diffusion: Transform and edit images using simple prompts with 100% local compute—no cloud uploads or external servers required - Dynamic Tooling & KV Cache Management:Your local LLM now receives a tailored toolbox for every interaction, with automatic KV cache clearing to maintain high-speed inference - Doctor CLI: A new diagnostic tool that analyzes your hardware and memory, providing specific instructions on how to optimize your GPU for local AI - Suspend & Resume API: Specifically designed for mobile environments, this allows apps to pause P2P swarms and RAG workspaces to meet background rules without losing model state - GPT-OSS Compatibility: Added support for the latest GPT-OSS models loaded externally, expanding the range of open-source intelligence available on the platform Build the future of private, unstoppable AI:

QVAC SDK 0.10.0 is now live, bringing advanced local compute capabilities and specialized hardware optimization directly to your device Key Features and Updates: - Image-to-Image Diffusion: Transform and edit images using simple prompts with 100% local compute—no cloud uploads or external servers required - Dynamic Tooling & KV Cache Management:Your local LLM now receives a tailored toolbox for every interaction, with automatic KV cache clearing to maintain high-speed inference - Doctor CLI: A new diagnostic tool that analyzes your hardware and memory, providing specific instructions on how to optimize your GPU for local AI - Suspend & Resume API: Specifically designed for mobile environments, this allows apps to pause P2P swarms and RAG workspaces to meet background rules without losing model state - GPT-OSS Compatibility: Added support for the latest GPT-OSS models loaded externally, expanding the range of open-source intelligence available on the platform Build the future of private, unstoppable AI:

QVAC

34,508 görüntüleme • 4 ay önce

QVAC SDK 0.13.0 is live, and this version brings a lot of exciting updates! Local AI now plugs into your coding agent, ships as a desktop app in one command, and runs even more models. Highlights: NEW INTEGRATIONS - OpenCode and coding agents: the new @qvac/ai-sdk-provider makes QVAC a local provider. Less setup, same-model requests queue cleanly, and managed mode starts and supervises qvac serve for you. - Broader OpenAI-compatible API, validated across supported flows so covered capabilities stay consistent and testable. - Turn your QVAC project into a real desktop app for Mac, Windows, or Linux with a single command. The new Electron plugin handles the packaging and keeps the app small by including only what it needs. NEW MODELS - New pi0.5 model support - run a vision-language "robot brain" on a single ordinary graphics card, at full accuracy. - Image-to-video, fully local, via the Wan2.1 model in the Diffusion addon. - New BCI add-on: brain-computer interface transcription, fully local. Decode recorded neural signals into text on-device via the Whisper.cpp-based BCI model. IMPROVEMENTS - Whisper GPU transcription on Android, auto-picking the best backend (OpenCL on Adreno 700+, Vulkan elsewhere), unified on one ggml engine. - Parakeet steadier on mobile, with real end-of-utterance detection for streaming. - Supertonic TTS now runs full GPU across Metal, Vulkan, and OpenCL, with native streaming.

QVAC SDK 0.13.0 is live, and this version brings a lot of exciting updates! Local AI now plugs into your coding agent, ships as a desktop app in one command, and runs even more models. Highlights: NEW INTEGRATIONS - OpenCode and coding agents: the new @qvac/ai-sdk-provider makes QVAC a local provider. Less setup, same-model requests queue cleanly, and managed mode starts and supervises qvac serve for you. - Broader OpenAI-compatible API, validated across supported flows so covered capabilities stay consistent and testable. - Turn your QVAC project into a real desktop app for Mac, Windows, or Linux with a single command. The new Electron plugin handles the packaging and keeps the app small by including only what it needs. NEW MODELS - New pi0.5 model support - run a vision-language "robot brain" on a single ordinary graphics card, at full accuracy. - Image-to-video, fully local, via the Wan2.1 model in the Diffusion addon. - New BCI add-on: brain-computer interface transcription, fully local. Decode recorded neural signals into text on-device via the Whisper.cpp-based BCI model. IMPROVEMENTS - Whisper GPU transcription on Android, auto-picking the best backend (OpenCL on Adreno 700+, Vulkan elsewhere), unified on one ggml engine. - Parakeet steadier on mobile, with real end-of-utterance detection for streaming. - Supertonic TTS now runs full GPU across Metal, Vulkan, and OpenCL, with native streaming.

QVAC

20,932,195 görüntüleme • 3 ay önce

QVAC SDK 0.15.0 is live. This release adds multiple prompts batching, brings a native AMD GPU backend to the stack, moves more vision encoders onto mobile GPUs, and adds a second local coding-agent integration. Main highlights: - Prompt batching for the LLM addon. Batch multiple prompts into one job and process them concurrently, with each answer returned the moment its generation finishes. - Native AMD GPU backend. A first-class HIP/ROCm backend in @qvac/vla-ggml, auto-selected over Vulkan with clean fallback when ROCm is absent. - A second local coding agent. OpenClaw joins OpenCode for local, cloud-free agent workflows. AGENTS - OpenCode plugin update (@qvac/opencode-plugin). Aligned with the current SDK, CLI, and AI SDK provider packages. A fresh install runs OpenCode against managed local QVAC models out of the box, from the default qvac/qwen3.5-9b, with no manual qvac serve setup. - OpenClaw plugin (@qvac/openclaw-plugin). A second coding-agent integration alongside OpenCode. A fresh setup installs the plugin, creates a local qvac provider through onboarding, and runs a QVAC model through OpenClaw🦞's local service path. LANGUAGE MODELS - Prompt batching (LLM addon). Batch multiple prompts in one job and run them concurrently, each answer returns the moment its generation finishes, no waiting on the others. - Reasoning-context trimming on hybrid + recurrent models (@qvac/llm-llamacpp). remove_thinking_from_context now works beyond pure-attention models. Same JS API, no throw. VOICE AND SPEECH - Transcription (transcription-parakeet 0.9.0). More robust CPU fallback on GPU failure and a faster Vulkan backend on Pixel 9. - Text-to-speech features (tts-ggml 0.4.0). Adds LavaSR for noise removal and adjustable output frequency up to 48 kHz, plus Japanese via Chatterbox. - Text-to-speech fixes (tts-ggml 0.4.1). CPU fallback on GPU failure, a q8_0 KV crash fix on Metal with Chatterbox. VISION - Qwen3.5 vision encoder on GPU (Android). Image encoder moves onto the phone GPU, with a smarter tile-grid preprocessor and default image-token caps, for flagship Android: Vulkan on Mali (Pixel 9 Pro) and OpenCL on Adreno 830 (Galaxy S25). - Gemma-4 vision encoder on GPU (Android). Vision encoder runs on the phone GPU instead of CPU, same flagship Android targets. PLATFORM AND PERFORMANCE - AMD GPU backend (@qvac/vla-ggml). Native HIP/ROCm backend, auto-selected over Vulkan with clean fallback when ROCm is absent (Linux x64 only). Comes with ~23% faster than Vulkan, ~14% faster than PyTorch-ROCm, parity preserved. Unified code style. A cleaner, more consistent, easier-to-contribute codebase. Let's build. npm install @qvac/sdk

QVAC SDK 0.15.0 is live. This release adds multiple prompts batching, brings a native AMD GPU backend to the stack, moves more vision encoders onto mobile GPUs, and adds a second local coding-agent integration. Main highlights: - Prompt batching for the LLM addon. Batch multiple prompts into one job and process them concurrently, with each answer returned the moment its generation finishes. - Native AMD GPU backend. A first-class HIP/ROCm backend in @qvac/vla-ggml, auto-selected over Vulkan with clean fallback when ROCm is absent. - A second local coding agent. OpenClaw joins OpenCode for local, cloud-free agent workflows. AGENTS - OpenCode plugin update (@qvac/opencode-plugin). Aligned with the current SDK, CLI, and AI SDK provider packages. A fresh install runs OpenCode against managed local QVAC models out of the box, from the default qvac/qwen3.5-9b, with no manual qvac serve setup. - OpenClaw plugin (@qvac/openclaw-plugin). A second coding-agent integration alongside OpenCode. A fresh setup installs the plugin, creates a local qvac provider through onboarding, and runs a QVAC model through OpenClaw🦞's local service path. LANGUAGE MODELS - Prompt batching (LLM addon). Batch multiple prompts in one job and run them concurrently, each answer returns the moment its generation finishes, no waiting on the others. - Reasoning-context trimming on hybrid + recurrent models (@qvac/llm-llamacpp). remove_thinking_from_context now works beyond pure-attention models. Same JS API, no throw. VOICE AND SPEECH - Transcription (transcription-parakeet 0.9.0). More robust CPU fallback on GPU failure and a faster Vulkan backend on Pixel 9. - Text-to-speech features (tts-ggml 0.4.0). Adds LavaSR for noise removal and adjustable output frequency up to 48 kHz, plus Japanese via Chatterbox. - Text-to-speech fixes (tts-ggml 0.4.1). CPU fallback on GPU failure, a q8_0 KV crash fix on Metal with Chatterbox. VISION - Qwen3.5 vision encoder on GPU (Android). Image encoder moves onto the phone GPU, with a smarter tile-grid preprocessor and default image-token caps, for flagship Android: Vulkan on Mali (Pixel 9 Pro) and OpenCL on Adreno 830 (Galaxy S25). - Gemma-4 vision encoder on GPU (Android). Vision encoder runs on the phone GPU instead of CPU, same flagship Android targets. PLATFORM AND PERFORMANCE - AMD GPU backend (@qvac/vla-ggml). Native HIP/ROCm backend, auto-selected over Vulkan with clean fallback when ROCm is absent (Linux x64 only). Comes with ~23% faster than Vulkan, ~14% faster than PyTorch-ROCm, parity preserved. Unified code style. A cleaner, more consistent, easier-to-contribute codebase. Let's build. npm install @qvac/sdk

QVAC

29,260,217 görüntüleme • 2 ay önce

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps. pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second. That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket. Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack. Watch and save it, then fine-tune your own tiny agent tonight.

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps. pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second. That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket. Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack. Watch and save it, then fine-tune your own tiny agent tonight.

h100envy

709,544 görüntüleme • 2 ay önce