Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Chinese startup EngineAI unveiled their SE01 prototype in October. Today, they've announced the beginning of sales for their smaller humanoid PM01. 4'6" tall, weighs 40kg, has 24 DoF, 2m/s walking speed, and supports R&D with X86 + NVIDIA Jetson Orin. Price: 88k RMB ($12,000)

The Humanoid Hub

66,684 subscribers

133,376 views • 1 year ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

11 Comments

l1 year ago

"4'6" tall" Damn , it's NEVER gonna get laid

ARK Electronics2 years ago

Excited about the latest tech for your drone product? Our NDAA-compliant, US-made flight controllers are designed to accelerate your path to market and provide a solid platform for developing your autonomous software. Check them out! #Drones #UAV #UAS #Robotics #MadeInUSA

Jim1 year ago

the walk is very human like, good work!

The Highly Automated Cat — e/acc ⏩1 year ago

the west is heading into a sputnik moment

Engineering Randomness1 year ago

The robotics companies need to fire any marketing people who make these videos look like 3D renders. Robot demos need to be outside, in the real world, with real people and lighting in view. The unitree video is incredible precisely because it is dirty and real!

Teku1 year ago

What’s the use case ? How good is it’s ai ?

The Humanoid Hub1 year ago

It’s a hardware platform for academic and commercial r&d, like Unitree.

Wolfe1 year ago

Lowkey walks like it’s Chinese

Tetsuro1 year ago

👀

Kikker1 year ago

Just make them stand up normally 🤬

AI and Robotics engineer1 year ago

12k is nothing for a robot!! These things will be everywhere

Related Videos

Like clockwork, another Chinese humanoid drops. Beijing-based NOETIX Robotics has unveiled the N2, a 3'7" tall humanoid weighing 20 kg (44 lb), with 18 DOF for the whole body and an NVIDIA Jetson installed. The price will start at ¥39,900 ($5,500).

Like clockwork, another Chinese humanoid drops. Beijing-based NOETIX Robotics has unveiled the N2, a 3'7" tall humanoid weighing 20 kg (44 lb), with 18 DOF for the whole body and an NVIDIA Jetson installed. The price will start at ¥39,900 ($5,500).

The Humanoid Hub

130,690 views • 1 year ago

$6,800 for a humanoid robot!! Unitree isn't just competing; they're resetting the entire market. The Unitree R1 Humanoid Robot is now available for pre-order on AliExpress for global buyers. Starting price of $6,806; deliveries are scheduled to begin on June 30th. 4'0" (123 cm) tall, 63.9 lb (29 kg). - R1 AIR (Base Trim): 20 Degrees of Freedom (DOF). - R1 & R1 EDU: 26 DOF (includes additional DOF in the waist and head). - R1 EDU: Only model that supports custom software installation and provides full SDK access. Optional upgrades include robotic hands and an NVIDIA Jetson Orin. The starting price applies to the base trim; pricing for the R1 and R1 EDU models has not yet been announced.

$6,800 for a humanoid robot!! Unitree isn't just competing; they're resetting the entire market. The Unitree R1 Humanoid Robot is now available for pre-order on AliExpress for global buyers. Starting price of $6,806; deliveries are scheduled to begin on June 30th. 4'0" (123 cm) tall, 63.9 lb (29 kg). - R1 AIR (Base Trim): 20 Degrees of Freedom (DOF). - R1 & R1 EDU: 26 DOF (includes additional DOF in the waist and head). - R1 EDU: Only model that supports custom software installation and provides full SDK access. Optional upgrades include robotic hands and an NVIDIA Jetson Orin. The starting price applies to the base trim; pricing for the R1 and R1 EDU models has not yet been announced.

The Humanoid Hub

261,894 views • 3 months ago

Chinese startup Leju Robotics has released their open-source humanoid development platform for academic and R&D use cases. It includes an SDK for sensors and controls, simulation models, an LLM interface, and some basic demos that work out-of-the-box.

Chinese startup Leju Robotics has released their open-source humanoid development platform for academic and R&D use cases. It includes an SDK for sensors and controls, simulation models, an LLM interface, and some basic demos that work out-of-the-box.

The Humanoid Hub

112,479 views • 1 year ago

NEWS: Chinese EV maker Xpeng today unveiled their humanoid robot named Iron that they've been working on for 5 years. Video below is not CGI. • 60+ joints & 200 total degrees of freedom • Tech shared from its vehicles • 5 foot 8 inches tall • Weighs 154 lbs (70kg) • Robots already integrated into Xpeng's daily operations, such as factories • Robot's brain is powered by Xpeng's Turing AI chip • Xpeng: "The end-to-end large model gives it the ability to walk, and fingers that can perform tasks including grasping, holding, and placing items." More info:

NEWS: Chinese EV maker Xpeng today unveiled their humanoid robot named Iron that they've been working on for 5 years. Video below is not CGI. • 60+ joints & 200 total degrees of freedom • Tech shared from its vehicles • 5 foot 8 inches tall • Weighs 154 lbs (70kg) • Robots already integrated into Xpeng's daily operations, such as factories • Robot's brain is powered by Xpeng's Turing AI chip • Xpeng: "The end-to-end large model gives it the ability to walk, and fingers that can perform tasks including grasping, holding, and placing items." More info:

Sawyer Merritt

928,019 views • 1 year ago

JUST IN: Unitree Robotics just unveiled the GD01, a manned "mecha" robot that transforms between two legs and four legs in real time. This is not a concept. This is a product. Starting price: $574,000. This robot weighs 500kg, is built from high-strength alloy, and has a torso-mounted cockpit. The demo video shows it walking upright, knocking down a brick wall with its hand, then reconfiguring into a four-legged crawl. Unitree calls it the world's first mass-produced transformable mecha. But the real story here is the bigger picture. Chinese companies accounted for nearly 90% of global humanoid robot sales in 2025. Unitree alone shipped 5,500+ humanoid robots last year. In the same period, Tesla, Figure AI and Agility Robotics each shipped around 150. And Unitree is now filing for an IPO on Shanghai's Star Market, targeting 4.2 billion yuan, 85% of which goes straight into R&D. The West is building incredible humanoid robots. China is building them faster, cheaper and at a scale nobody else is close to matching. Read more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

JUST IN: Unitree Robotics just unveiled the GD01, a manned "mecha" robot that transforms between two legs and four legs in real time. This is not a concept. This is a product. Starting price: $574,000. This robot weighs 500kg, is built from high-strength alloy, and has a torso-mounted cockpit. The demo video shows it walking upright, knocking down a brick wall with its hand, then reconfiguring into a four-legged crawl. Unitree calls it the world's first mass-produced transformable mecha. But the real story here is the bigger picture. Chinese companies accounted for nearly 90% of global humanoid robot sales in 2025. Unitree alone shipped 5,500+ humanoid robots last year. In the same period, Tesla, Figure AI and Agility Robotics each shipped around 150. And Unitree is now filing for an IPO on Shanghai's Star Market, targeting 4.2 billion yuan, 85% of which goes straight into R&D. The West is building incredible humanoid robots. China is building them faster, cheaper and at a scale nobody else is close to matching. Read more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

11,580 views • 2 months ago

Today was very special for Bryan and I to stand tall with and for the People of Iran. Thank you to Darya Safai for inviting me and allowing us to pray together for the tens of thousands of Iranians murdered by this “sick” regime, as President Trump has said of them. As US Ambassador to Belgium, the USA supports the will of the Iranian people for a better future. While we have interacted with many external opposition figures, we want to be clear that, as The President has said, the U.S. does specifically not endorse Reza Pahlavi or any specific opposition leader. Rather, we wholeheartedly support the will of the Iranian people in Iran for a better future for them and their families. I met three mothers whose sons were killed by the regime for simply walking in the streets holding candles for peace. We took a moment of silence for all those who have been killed. We stand with the great people of Iran.

Today was very special for Bryan and I to stand tall with and for the People of Iran. Thank you to Darya Safai for inviting me and allowing us to pray together for the tens of thousands of Iranians murdered by this “sick” regime, as President Trump has said of them. As US Ambassador to Belgium, the USA supports the will of the Iranian people for a better future. While we have interacted with many external opposition figures, we want to be clear that, as The President has said, the U.S. does specifically not endorse Reza Pahlavi or any specific opposition leader. Rather, we wholeheartedly support the will of the Iranian people in Iran for a better future for them and their families. I met three mothers whose sons were killed by the regime for simply walking in the streets holding candles for peace. We took a moment of silence for all those who have been killed. We stand with the great people of Iran.

U.S. Ambassador to Belgium Bill White

320,874 views • 6 months ago

🚨 This viral bionic humanoid robot company just raised hundreds of millions RMB in funding ,and it may have finally crossed the Uncanny Valley AheadForm, the startup behind those ultra-realistic face robots that have racked up hundreds of millions of views across social media, just closed a massive A1 round. This new funding will accelerate bringing these wildly popular humanoid robots into everyday life. Worth noting: Founder Yuhang Hu's latest paper on realistic lip motions for humanoid face robots has landed on the cover of Science Robotics (Jan 2026 issue). Using self-supervised AI, their robots now generate incredibly natural, continuous lip sync,supporting multiple languages, different speaking speeds, emotions, and even singing. Powered by soft silicone skin and 10+ DoF actuators, gone are the stiff puppet faces. This marks a major leap toward truly empathetic, “alive” human-robot interaction. While factories and warehouses will be filled with heavy duty, rugged humanoids for labor, Companies like AheadForm is building the warm, emotionally intelligent ones for people,the kind that can smile, make eye contact, and create real connection. The future isn’t just efficient. It’s getting warmer.

🚨 This viral bionic humanoid robot company just raised hundreds of millions RMB in funding ,and it may have finally crossed the Uncanny Valley AheadForm, the startup behind those ultra-realistic face robots that have racked up hundreds of millions of views across social media, just closed a massive A1 round. This new funding will accelerate bringing these wildly popular humanoid robots into everyday life. Worth noting: Founder Yuhang Hu's latest paper on realistic lip motions for humanoid face robots has landed on the cover of Science Robotics (Jan 2026 issue). Using self-supervised AI, their robots now generate incredibly natural, continuous lip sync,supporting multiple languages, different speaking speeds, emotions, and even singing. Powered by soft silicone skin and 10+ DoF actuators, gone are the stiff puppet faces. This marks a major leap toward truly empathetic, “alive” human-robot interaction. While factories and warehouses will be filled with heavy duty, rugged humanoids for labor, Companies like AheadForm is building the warm, emotionally intelligent ones for people,the kind that can smile, make eye contact, and create real connection. The future isn’t just efficient. It’s getting warmer.

CyberRobo

112,752 views • 4 months ago

New "superman" Four months later, Shanghai-based Matrix Robotics unveiled the Matrix-3--yet another anthropomorphic humanoid robot situated on the left side of the "Uncanny Valley." Unlike Boston Dynamics' Atlas, which is designed for industrial settings, the Matrix-3 is a general-purpose humanoid robot intended initially for service-oriented environments such as supermarkets, hotels, and office buildings. Standing 1.7 meters tall and weighing 65 kilograms, the adult-sized robot features a full-body covering of biomimetic fabric integrated with tactile sensors, as well as humanoid biomimetic muscles. It employs linear joints rather than the mainstream rotary joints. Matrix claims it is capable of pulling or pushing a load of 200 kg. Optimus makes extensive use of linear joints (linear actuators). It is equipped with dexterous hands offering 27 DOF and boasts a battery life of 4 hours. The robot is powered by a model named WAVE(like an E2E World Action Model) Matrix states that it has already established a manufacturing facility in Shanghai's Zhangjiang with an annual production capacity of 10,000 units. The company plans to deliver 1,000 units this year, with the first batch scheduled for delivery by the end of June. Pricing starts at $99,000. Notably, Matrix founder Zhang Haixing previously served as a leader at Tesla China's Design and Research Center, where he was deeply involved in the early-stage R&D and design of the Optimus robot. This company seems to be delivering on the future envisioned for Optimus.

New "superman" Four months later, Shanghai-based Matrix Robotics unveiled the Matrix-3--yet another anthropomorphic humanoid robot situated on the left side of the "Uncanny Valley." Unlike Boston Dynamics' Atlas, which is designed for industrial settings, the Matrix-3 is a general-purpose humanoid robot intended initially for service-oriented environments such as supermarkets, hotels, and office buildings. Standing 1.7 meters tall and weighing 65 kilograms, the adult-sized robot features a full-body covering of biomimetic fabric integrated with tactile sensors, as well as humanoid biomimetic muscles. It employs linear joints rather than the mainstream rotary joints. Matrix claims it is capable of pulling or pushing a load of 200 kg. Optimus makes extensive use of linear joints (linear actuators). It is equipped with dexterous hands offering 27 DOF and boasts a battery life of 4 hours. The robot is powered by a model named WAVE(like an E2E World Action Model) Matrix states that it has already established a manufacturing facility in Shanghai's Zhangjiang with an annual production capacity of 10,000 units. The company plans to deliver 1,000 units this year, with the first batch scheduled for delivery by the end of June. Pricing starts at $99,000. Notably, Matrix founder Zhang Haixing previously served as a leader at Tesla China's Design and Research Center, where he was deeply involved in the early-stage R&D and design of the Optimus robot. This company seems to be delivering on the future envisioned for Optimus.

CyberRobo

40,727 views • 2 months ago

ElevenLabs CEO: Why Voice is the Next AI Interface ElevenLabs is one of the most interesting companies in AI today. In just three years, they’ve gone from two cofounders from Poland to dominating the AI voice industry. ElevenLabs does their own R&D, builds their own foundation models, and ships over 10 different products at lightning speed without compromising on quality. We sat down with ElevenLabs co-founder and CEO Mati Staniszewski to discuss the breadth of their product roadmap, why they aren’t based in SF, how they’re working to overcome opposition in creative industries, and the hardest parts of Mati’s journey from small startup founder to industry titan. 00:00 Intro 02:50 Early research and product work with Piotr 03:35 Shipping quickly with small, high ownership independent teams 04:40 Balancing research and product launches 06:50 A remote-first approach: meeting talent where they are 10:00 US vs Europe work cultures 13:35 The creative industry’s adoption of AI 16:43 Challenges in licensing and 18-month negotiation process 18:05 Hiring in complex domains 20:45 Transitioning from creator-first to enterprise adoption 21:48 Lessons from hiring the first salespeople 23:34 Scaling orchestration, long sales cycles and cultural adjustments 26:22 Customer choice in adopting early features 27:55 Phases of company growth: product, sales, scaling Jennifer Li

ElevenLabs CEO: Why Voice is the Next AI Interface ElevenLabs is one of the most interesting companies in AI today. In just three years, they’ve gone from two cofounders from Poland to dominating the AI voice industry. ElevenLabs does their own R&D, builds their own foundation models, and ships over 10 different products at lightning speed without compromising on quality. We sat down with ElevenLabs co-founder and CEO Mati Staniszewski to discuss the breadth of their product roadmap, why they aren’t based in SF, how they’re working to overcome opposition in creative industries, and the hardest parts of Mati’s journey from small startup founder to industry titan. 00:00 Intro 02:50 Early research and product work with Piotr 03:35 Shipping quickly with small, high ownership independent teams 04:40 Balancing research and product launches 06:50 A remote-first approach: meeting talent where they are 10:00 US vs Europe work cultures 13:35 The creative industry’s adoption of AI 16:43 Challenges in licensing and 18-month negotiation process 18:05 Hiring in complex domains 20:45 Transitioning from creator-first to enterprise adoption 21:48 Lessons from hiring the first salespeople 23:34 Scaling orchestration, long sales cycles and cultural adjustments 26:22 Customer choice in adopting early features 27:55 Phases of company growth: product, sales, scaling Jennifer Li

a16z

144,000 views • 9 months ago

This is what Democrats have done to Minneapolis, Minnesota Crime and drug sales have gotten so bad, private security companies for apartment complexes are pulling contracts and no longer servicing the area “Monday, I get a text from my property management company saying that they've retained an outside security company to address the numerous complaints about loitering and drug sales in the neighborhood. ‘Beginning today, you will see these security personnel around the properties and in the neighborhood goes on and on about procedures’ Okay. Today's Wednesday. It's two days later, I get an email from my property management company, and they said, we're disappointed to share that the security company that was hired has pulled out of the neighborhood. ‘After a day and a half of doing recon and observing activity in the neighborhood, they decided the problems with crime exceed their resources to control. We will continue to work with organizations and neighborhood and explore other options to improve public safety’”

This is what Democrats have done to Minneapolis, Minnesota Crime and drug sales have gotten so bad, private security companies for apartment complexes are pulling contracts and no longer servicing the area “Monday, I get a text from my property management company saying that they've retained an outside security company to address the numerous complaints about loitering and drug sales in the neighborhood. ‘Beginning today, you will see these security personnel around the properties and in the neighborhood goes on and on about procedures’ Okay. Today's Wednesday. It's two days later, I get an email from my property management company, and they said, we're disappointed to share that the security company that was hired has pulled out of the neighborhood. ‘After a day and a half of doing recon and observing activity in the neighborhood, they decided the problems with crime exceed their resources to control. We will continue to work with organizations and neighborhood and explore other options to improve public safety’”

Wall Street Apes

324,197 views • 1 year ago

China unveils humanoid robot worker with brain that runs 275 trillion ops/sec | Jijo Malayil, Interesting Engineering In tests, SUYUAN used vision and joint control to sort and move crates of various sizes, greatly improving warehouse productivity. Chinese manufacturing firm Shanghai Electric has unveiled its first self-developed industrial humanoid robot, “SUYUAN,” marking a major milestone in its robotics journey. Debuting at the World Artificial Intelligence Conference (WAIC 2025) on July 26 in Shanghai, SUYUAN boasts 38 degrees of freedom and 275 TOPS of on-device computing power, enabling precise operations and fluid movements. According to the firm, designed for diverse industrial use, the robot showcases Shanghai Electric’s end-to-end capabilities—from core tech to integrated solutions—and reinforces its commitment to next-gen industrial automation through a full industry chain strategy. At WAIC 2025, Shanghai Electric also unveiled a new joint venture with Johnson Electric for next-gen humanoid robotics and showcased its “LINGKE” dual-arm robot. Recently, Hangzhou-based Unitree Robotics launched the R1 humanoid with 26 joints for $5,900, showcasing athletic feats like cartwheels, running, and quick recovery. Smart factory assistant Shanghai Electric claims SUYUAN, equipped with 38 degrees of freedom (DoF) and a powerful 275 TOPS on-device computing processor, delivers fluid, human-like movements and high-precision operations across various industrial scenarios. Its advanced articulation and real-time processing capabilities make it highly adaptable, enabling smooth execution of complex tasks in dynamic work environments. SUYUAN, who weighs 110 pounds (50 kilograms) and is 5 feet 6 inches (167 cm) tall, was designed to have human-like proportions. Its 38-DoF articulation offers dexterity, allowing for both wide-range motion and sensitive manipulation. With a single arm, the robot can lift objects up to 4.4 pounds (2 kilograms) in weight and carry a total payload of up to 22 pounds (10 kilograms). With a walking pace of 3.1 miles per hour (5 km/h), SUYUAN is ideal for environments including assembly lines, warehousing, and logistics, according to a statement. To navigate complex industrial settings, SUYUAN combines LiDAR and binocular vision for self-guided mobility. Its 275-TOPS AI processor enables rapid data analysis and integration with large language models, allowing it to understand tasks in natural language and handle objects adaptively, reports Fox 44 News. In pilot demonstrations, the robot successfully identified, picked, and relocated crates of varying sizes using advanced computer vision and coordinated joint control—delivering measurable gains in warehouse efficiency. The company claims that SUYUAN’s launch represents a major turning point in Shanghai Electric’s foray into humanoid robotics and strengthens its vertically integrated approach to industrial automation solutions. Intelligent task handling Shanghai Electric also demonstrated its most recent developments in intelligent manufacturing at WAIC 2025, introducing a new joint venture with Johnson Electric centered on next-generation humanoid robotics and showcasing the “LINGKE” dual-arm robot. With its high-precision operations, adaptive teamwork, and closed-loop data capabilities, the LINGKE robot demonstrated live talents in handling complicated production jobs. LINGKE is made to do more than just replace human labor; it uses compliant force control and bimanual coordination to relieve workers of high-intensity, repetitive jobs. According to the company, the robot enhances operational efficiency by up to five times. Its core strength lies in a Data-Model-Deployment closed-loop system that starts with operational data, followed by data cleansing, model training, live deployment, and feedback-driven optimization—enabling autonomous learning and workflow improvement. Also at the event, Shanghai Electric and Johnson Electric introduced advanced hardware modules for humanoid robots, including rotary joints, linear joints, and dexterous finger joints. These components are designed to support smooth, precise, and quiet motion performance across robotics systems, reports Stock Titan. The joint venture announced two strategic agreements: a first-unit supply deal with the National and Local Co-Built Humanoid Robotics Innovation Center (Qinglong Project) and a cooperation memorandum with Fourier Robotics. Read more:

China unveils humanoid robot worker with brain that runs 275 trillion ops/sec | Jijo Malayil, Interesting Engineering In tests, SUYUAN used vision and joint control to sort and move crates of various sizes, greatly improving warehouse productivity. Chinese manufacturing firm Shanghai Electric has unveiled its first self-developed industrial humanoid robot, “SUYUAN,” marking a major milestone in its robotics journey. Debuting at the World Artificial Intelligence Conference (WAIC 2025) on July 26 in Shanghai, SUYUAN boasts 38 degrees of freedom and 275 TOPS of on-device computing power, enabling precise operations and fluid movements. According to the firm, designed for diverse industrial use, the robot showcases Shanghai Electric’s end-to-end capabilities—from core tech to integrated solutions—and reinforces its commitment to next-gen industrial automation through a full industry chain strategy. At WAIC 2025, Shanghai Electric also unveiled a new joint venture with Johnson Electric for next-gen humanoid robotics and showcased its “LINGKE” dual-arm robot. Recently, Hangzhou-based Unitree Robotics launched the R1 humanoid with 26 joints for $5,900, showcasing athletic feats like cartwheels, running, and quick recovery. Smart factory assistant Shanghai Electric claims SUYUAN, equipped with 38 degrees of freedom (DoF) and a powerful 275 TOPS on-device computing processor, delivers fluid, human-like movements and high-precision operations across various industrial scenarios. Its advanced articulation and real-time processing capabilities make it highly adaptable, enabling smooth execution of complex tasks in dynamic work environments. SUYUAN, who weighs 110 pounds (50 kilograms) and is 5 feet 6 inches (167 cm) tall, was designed to have human-like proportions. Its 38-DoF articulation offers dexterity, allowing for both wide-range motion and sensitive manipulation. With a single arm, the robot can lift objects up to 4.4 pounds (2 kilograms) in weight and carry a total payload of up to 22 pounds (10 kilograms). With a walking pace of 3.1 miles per hour (5 km/h), SUYUAN is ideal for environments including assembly lines, warehousing, and logistics, according to a statement. To navigate complex industrial settings, SUYUAN combines LiDAR and binocular vision for self-guided mobility. Its 275-TOPS AI processor enables rapid data analysis and integration with large language models, allowing it to understand tasks in natural language and handle objects adaptively, reports Fox 44 News. In pilot demonstrations, the robot successfully identified, picked, and relocated crates of varying sizes using advanced computer vision and coordinated joint control—delivering measurable gains in warehouse efficiency. The company claims that SUYUAN’s launch represents a major turning point in Shanghai Electric’s foray into humanoid robotics and strengthens its vertically integrated approach to industrial automation solutions. Intelligent task handling Shanghai Electric also demonstrated its most recent developments in intelligent manufacturing at WAIC 2025, introducing a new joint venture with Johnson Electric centered on next-generation humanoid robotics and showcasing the “LINGKE” dual-arm robot. With its high-precision operations, adaptive teamwork, and closed-loop data capabilities, the LINGKE robot demonstrated live talents in handling complicated production jobs. LINGKE is made to do more than just replace human labor; it uses compliant force control and bimanual coordination to relieve workers of high-intensity, repetitive jobs. According to the company, the robot enhances operational efficiency by up to five times. Its core strength lies in a Data-Model-Deployment closed-loop system that starts with operational data, followed by data cleansing, model training, live deployment, and feedback-driven optimization—enabling autonomous learning and workflow improvement. Also at the event, Shanghai Electric and Johnson Electric introduced advanced hardware modules for humanoid robots, including rotary joints, linear joints, and dexterous finger joints. These components are designed to support smooth, precise, and quiet motion performance across robotics systems, reports Stock Titan. The joint venture announced two strategic agreements: a first-unit supply deal with the National and Local Co-Built Humanoid Robotics Innovation Center (Qinglong Project) and a cooperation memorandum with Fourier Robotics. Read more:

Owen Gregorian

51,638 views • 1 year ago

A truly staggering number of AI-powered humanoid robots are emerging from Shenzhen, the booming Chinese tech hub. Shenzhen Dobot, which rose from a Kickstarter campaign to become an industrial automation leader, says its first humanoid robot, Atom, has entered mass production. Atom is positioned as a general-purpose cross-industry worker. Priced around $27,000, Atom boasts fine motor control that’s precise enough to pick up a cherry by the stem. Another major player is Pudu Robotics, which recently shipped its 100,000th service robot. Pudu is commercializing its wheeled and bipedal humanoids using its sizable customer base. Its flagship is the PUDU D9, a full-sized biped built to serve in places like warehouses, stores, and hotels. It sells for between $20,000 and $30,000. A newer firm, AI Squared, recently closed a funding round worth hundreds of millions of yuan to rush its Alpha Bot 2 general-purpose humanoid to market. The startup, founded in 2023, says its AI combines slow reasoning and fast motion planning so its robots can plan, talk, and move simultaneously. An even newer firm, Lumos Robotics, has reportedly raised nearly $28 million in angel funding to develop a full-stack humanoid robotics platform. The second-generation iteration of its flagship robot, the LUS 2, recently demonstrated the ability to get up from the ground in just a second. According to Lumos, the next-gen bot features upgraded actuators and sensors for athletic-level dexterity. LimX Dynamics, known for its agile quadrupeds and bipeds, just shared footage showcasing its CL-3 humanoid’s lifelike walking gait and gestures. LimX says its flagship humanoid can watch human movement videos and replicate them via motion conversion, with no hand coding required. Just a year after its establishment, the startup DIGIT has unveiled multiple lines of sci-fi-inspired humanoids. Its Starwalker robots switch between legged and wheeled locomotion to cover more than 10,000 square meters across multiple floors. They’re available in five different colors. DIGIT also has a robot named Xia Lan with a humanlike face that can show a range of expressions and emotions. The leading Chinese robotics firm UBTECH also recently introduced its first hyper-realistic humanoid robot, Una, intended for applications like customer service and event marketing. UBTECH says it’s begun mass-producing its Walker S humanoid robots that are reportedly helping assemble iPhones for Foxconn. Footage of a so-called intelligent swarm of these humanoids at a Zeekr factory shocked the world. Another EV maker, Xpeng, plans to start mass-producing its Iron humanoids in 2026. The robot reportedly stole the show during the 2025 Shanghai Auto Week. The Shenzhen firm that’s gotten the most attention outside the usual tech echo chambers is Engine AI, which is planning the world’s first full-sized humanoid robot boxing tournament.

A truly staggering number of AI-powered humanoid robots are emerging from Shenzhen, the booming Chinese tech hub. Shenzhen Dobot, which rose from a Kickstarter campaign to become an industrial automation leader, says its first humanoid robot, Atom, has entered mass production. Atom is positioned as a general-purpose cross-industry worker. Priced around $27,000, Atom boasts fine motor control that’s precise enough to pick up a cherry by the stem. Another major player is Pudu Robotics, which recently shipped its 100,000th service robot. Pudu is commercializing its wheeled and bipedal humanoids using its sizable customer base. Its flagship is the PUDU D9, a full-sized biped built to serve in places like warehouses, stores, and hotels. It sells for between $20,000 and $30,000. A newer firm, AI Squared, recently closed a funding round worth hundreds of millions of yuan to rush its Alpha Bot 2 general-purpose humanoid to market. The startup, founded in 2023, says its AI combines slow reasoning and fast motion planning so its robots can plan, talk, and move simultaneously. An even newer firm, Lumos Robotics, has reportedly raised nearly $28 million in angel funding to develop a full-stack humanoid robotics platform. The second-generation iteration of its flagship robot, the LUS 2, recently demonstrated the ability to get up from the ground in just a second. According to Lumos, the next-gen bot features upgraded actuators and sensors for athletic-level dexterity. LimX Dynamics, known for its agile quadrupeds and bipeds, just shared footage showcasing its CL-3 humanoid’s lifelike walking gait and gestures. LimX says its flagship humanoid can watch human movement videos and replicate them via motion conversion, with no hand coding required. Just a year after its establishment, the startup DIGIT has unveiled multiple lines of sci-fi-inspired humanoids. Its Starwalker robots switch between legged and wheeled locomotion to cover more than 10,000 square meters across multiple floors. They’re available in five different colors. DIGIT also has a robot named Xia Lan with a humanlike face that can show a range of expressions and emotions. The leading Chinese robotics firm UBTECH also recently introduced its first hyper-realistic humanoid robot, Una, intended for applications like customer service and event marketing. UBTECH says it’s begun mass-producing its Walker S humanoid robots that are reportedly helping assemble iPhones for Foxconn. Footage of a so-called intelligent swarm of these humanoids at a Zeekr factory shocked the world. Another EV maker, Xpeng, plans to start mass-producing its Iron humanoids in 2026. The robot reportedly stole the show during the 2025 Shanghai Auto Week. The Shenzhen firm that’s gotten the most attention outside the usual tech echo chambers is Engine AI, which is planning the world’s first full-sized humanoid robot boxing tournament.

Mike Kalil

11,408 views • 1 year ago

Philippine Coast Guard Continues Vigilant Patrols in Zambales Against Illegal Patrols of China Coast Guard Today, the Philippine Coast Guard vessel, BRP Cabra, under the command of LCDR Hanna Yanez, a female skipper, is actively patrolling off the coast of Zambales to thwart attempts by the China Coast Guard to normalize their illegal patrols within the Philippines' Exclusive Economic Zone (EEZ). Despite the BRP Cabra being smaller in length compared to the Chinese Coast Guard vessels, PCG Commandant Admiral Ronnie Gil Gavan asserts that international law empowers our vessel to operate without intimidation. This confidence allows the BRP Cabra to challenge the China Coast Guard, thereby exposing their unruly behavior and bullying tactics to the international community. The Philippine Coast Guard conducts its maritime patrols in accordance with the United Nations Convention on the Law of the Sea (UNCLOS), the 2016 Arbitral Award, and the Philippine Maritime Zones Act. Yesterday, during an engagement with CCG-21612 in the vicinity of 132.97 WSW off Capon Grande, Zambales, or approximately 36.35 S off BDM, the Chinese Coast Guard increased its speed and maneuvered past the port side of the BRP Cabra, dangerously blocking its navigation route. This incident highlights the CCG's non-compliance with the International Regulations for Preventing Collisions at Sea (COLREGS) and reflects a blatant disregard for safety at sea. While coast guards are typically recognized as enforcers of maritime safety and humanitarian organizations, the actions of the People's Republic of China diverge from these norms. Their illegal patrols jeopardize the lives of fishermen and legitimate law enforcement agencies alike. The Philippine Coast Guard remains committed to supporting the policy direction of President Ferdinand R. Marcos, Jr. that is to assert our rights and jurisdiction while ensuring that we do not act as an agent of escalation in the West Philippine Sea.

Philippine Coast Guard Continues Vigilant Patrols in Zambales Against Illegal Patrols of China Coast Guard Today, the Philippine Coast Guard vessel, BRP Cabra, under the command of LCDR Hanna Yanez, a female skipper, is actively patrolling off the coast of Zambales to thwart attempts by the China Coast Guard to normalize their illegal patrols within the Philippines' Exclusive Economic Zone (EEZ). Despite the BRP Cabra being smaller in length compared to the Chinese Coast Guard vessels, PCG Commandant Admiral Ronnie Gil Gavan asserts that international law empowers our vessel to operate without intimidation. This confidence allows the BRP Cabra to challenge the China Coast Guard, thereby exposing their unruly behavior and bullying tactics to the international community. The Philippine Coast Guard conducts its maritime patrols in accordance with the United Nations Convention on the Law of the Sea (UNCLOS), the 2016 Arbitral Award, and the Philippine Maritime Zones Act. Yesterday, during an engagement with CCG-21612 in the vicinity of 132.97 WSW off Capon Grande, Zambales, or approximately 36.35 S off BDM, the Chinese Coast Guard increased its speed and maneuvered past the port side of the BRP Cabra, dangerously blocking its navigation route. This incident highlights the CCG's non-compliance with the International Regulations for Preventing Collisions at Sea (COLREGS) and reflects a blatant disregard for safety at sea. While coast guards are typically recognized as enforcers of maritime safety and humanitarian organizations, the actions of the People's Republic of China diverge from these norms. Their illegal patrols jeopardize the lives of fishermen and legitimate law enforcement agencies alike. The Philippine Coast Guard remains committed to supporting the policy direction of President Ferdinand R. Marcos, Jr. that is to assert our rights and jurisdiction while ensuring that we do not act as an agent of escalation in the West Philippine Sea.

Jay Tarriela

14,641 views • 1 year ago

I sat down with Brett Adcock, CEO and Founder of Figure AI, to discuss the future of humanoid robots. In less than three years since its inception, Figure has built versions 01 and 02 of their humanoids, developed a foundation model called Helix AI to reason like humans, shipped robots into the factories of their commercial customers, and is now valued at $39.5 billion according to their latest funding round. Brett is a founder who wants to win. In the podcast, we dive deeper into where that drive comes from, how he envisions the future of humanity if billions of robots walk the planet, and why he believes this is the single biggest opportunity of our lifetime. It was a privilege to visit the HQ and have the chance to speak with him. Occasionally during the podcast, you’ll see a Figure 02 walking autonomously behind us! It truly was a one-of-a-kind experience to be so close to the robots that will eventually be part of our everyday lives. Thank you Brett Adcock for taking the time & I'm so excited to follow your journey as you build one of the most important companies of our time. LFG. Timestamps below: 00:00 - Who Is Brett? 01:51 - The First Startup 05:46 - SaaS to DeepTech 07:21 - Why Robots? 13:50 - The Business of Humanoids 19:06 - The Role of Nvidia in Robots 20:31 - Training Models for Bots 20:21 - OpenAI Collaboration 29:26 - Is There A Chip on Brett's Shoulder? 31:15 - Culture at Figure 40:35 - Tesla's Humanoid Ambitions 50:45 - Rapid Fire

I sat down with Brett Adcock, CEO and Founder of Figure AI, to discuss the future of humanoid robots. In less than three years since its inception, Figure has built versions 01 and 02 of their humanoids, developed a foundation model called Helix AI to reason like humans, shipped robots into the factories of their commercial customers, and is now valued at $39.5 billion according to their latest funding round. Brett is a founder who wants to win. In the podcast, we dive deeper into where that drive comes from, how he envisions the future of humanity if billions of robots walk the planet, and why he believes this is the single biggest opportunity of our lifetime. It was a privilege to visit the HQ and have the chance to speak with him. Occasionally during the podcast, you’ll see a Figure 02 walking autonomously behind us! It truly was a one-of-a-kind experience to be so close to the robots that will eventually be part of our everyday lives. Thank you Brett Adcock for taking the time & I'm so excited to follow your journey as you build one of the most important companies of our time. LFG. Timestamps below: 00:00 - Who Is Brett? 01:51 - The First Startup 05:46 - SaaS to DeepTech 07:21 - Why Robots? 13:50 - The Business of Humanoids 19:06 - The Role of Nvidia in Robots 20:31 - Training Models for Bots 20:21 - OpenAI Collaboration 29:26 - Is There A Chip on Brett's Shoulder? 31:15 - Culture at Figure 40:35 - Tesla's Humanoid Ambitions 50:45 - Rapid Fire

amit

676,769 views • 1 year ago

Demystifying China's Dancing Robots: How Did They Catch Handkerchiefs?🇨🇳🤖 16 humanoid robots from Chinese robotics company, Unitree, took center stage at the annual #SpringFestivalGala. The robots seamlessly coordinated with 16 human dancers to perform a traditional Yangko dance, a vibrant folk art form from northeast China, blending cultural heritage with cutting-edge technology. One of the most captivating moments came when the robots showcased their ability to manipulate handkerchiefs, a signature element of Yangko dance. With precise mechanical arm movements, the robots sent the handkerchiefs twirling and soaring through the air, creating a dazzling visual spectacle that symbolized the perfect fusion of tradition and modernity. To maintain the stable upright standing position is already a challenge for current humanoid robots – consider the shaky steps and tendency to roll off even a small incline of Elon Musk's Optimus. To toss a handkerchief and catch it back in place requires the integration of sensors, algorithm and smart design. "We've designed a very clever mechanism that integrates multiple AI control algorithms. There are two motors at the end of the robotic arm: one maintains a high-speed spinning motion, while the other ensures that the handkerchief can be thrown out and then retracted," Unitree's marketing representative said. The 16 humanoid robots belong to Unitree's H1 series, nicknamed Fuxi. Standing at 1.8 meters tall and weighing 47 kilograms, the robots took the stage at the Spring Festival Gala stage over a year after debuting in August 2023. They also attended the NVIDIA GTC conference in 2024. #ChineseNewYear #DeepSeek (Link:

Demystifying China's Dancing Robots: How Did They Catch Handkerchiefs?🇨🇳🤖 16 humanoid robots from Chinese robotics company, Unitree, took center stage at the annual #SpringFestivalGala. The robots seamlessly coordinated with 16 human dancers to perform a traditional Yangko dance, a vibrant folk art form from northeast China, blending cultural heritage with cutting-edge technology. One of the most captivating moments came when the robots showcased their ability to manipulate handkerchiefs, a signature element of Yangko dance. With precise mechanical arm movements, the robots sent the handkerchiefs twirling and soaring through the air, creating a dazzling visual spectacle that symbolized the perfect fusion of tradition and modernity. To maintain the stable upright standing position is already a challenge for current humanoid robots – consider the shaky steps and tendency to roll off even a small incline of Elon Musk's Optimus. To toss a handkerchief and catch it back in place requires the integration of sensors, algorithm and smart design. "We've designed a very clever mechanism that integrates multiple AI control algorithms. There are two motors at the end of the robotic arm: one maintains a high-speed spinning motion, while the other ensures that the handkerchief can be thrown out and then retracted," Unitree's marketing representative said. The 16 humanoid robots belong to Unitree's H1 series, nicknamed Fuxi. Standing at 1.8 meters tall and weighing 47 kilograms, the robots took the stage at the Spring Festival Gala stage over a year after debuting in August 2023. They also attended the NVIDIA GTC conference in 2024. #ChineseNewYear #DeepSeek (Link:

Li Jingjing 李菁菁

11,169 views • 1 year ago

MEET THE NVIDIA KILLER: OpenAI bet $10 BILLION on this company that makes chips 20x faster than Nvidia's. If this plays out as expected, it’s over for Nvidia. Cerebras Systems just locked in 750 megawatts of computing power to OpenAI through 2028. For reference: that's equivalent to the annual power consumption of 600,000 US homes. The deal? Over $10 billion. Here's what nobody understands: Cerebras doesn't make normal chips. Nvidia sells you thousands of tiny chips that you connect together. Cerebras makes ONE chip. A single wafer-scale processor the size of a dinner plate. 900,000 AI cores. 4 trillion transistors. All on one piece of silicon. The result? When OpenAI tested it, Cerebras ran inference 20X FASTER than Nvidia GPUs. That's not incremental improvement. That's a different category of performance. But here's where the story gets wild: Four months ago, Cerebras was a struggling company. Their IPO filing revealed that 87% of their revenue came from ONE customer: G42, a UAE-based AI firm. The US government launched a national security review. G42 had ties to Huawei. Ties to China. The IPO collapsed. Investors panicked. Cerebras withdrew their filing in October 2025. Most startups would've been dead. Instead, Cerebras did the opposite. They raised $1.1 billion at an $8.1 billion valuation. Kicked G42 out of the cap table entirely. Got CFIUS clearance. Then landed the OpenAI deal. Now they're raising ANOTHER $1 billion at a $22 billion valuation. They more than DOUBLED their valuation in 4 months. From near-death to $22 billion. While getting rid of their biggest customer. Why OpenAI chose them: ChatGPT has 900 million weekly users. Sam Altman keeps saying they have a "severe shortage" of compute. They need SPEED, not just power. When you ask ChatGPT a question, there's a loop happening: You send request → model thinks → sends response back Nvidia chips are fast at training models. Cerebras chips are built specifically for inference. For real-time responses. For the exact bottleneck OpenAI is trying to solve. Sachin Katti from OpenAI said it best: "Cerebras adds a dedicated low-latency inference solution to our platform. That means faster responses, more natural interactions, and a stronger foundation to scale real-time AI to many more people." In other words: "We need this to scale ChatGPT." The competitive landscape just shifted: Nvidia announced a $100 billion deal with OpenAI in September. But it's still not finalized. Meanwhile, Cerebras closed their deal before Thanksgiving. And it's ALREADY being deployed. Here's the part that should terrify Nvidia: In December, Nvidia bought Groq for $20 billion. Groq makes fast inference chips. Just like Cerebras. So why would Nvidia spend $20 billion buying a competitor to something they supposedly already dominate? Because they know what's coming. Inference is the new battleground. And Cerebras is winning it. The IPO is coming Q2 2026. After this OpenAI deal, Cerebras now has: ✓ IBM contracts ✓ Department of Energy contracts ✓ OpenAI locked in for 3 years ✓ $22 billion valuation ✓ CFIUS clearance ✓ Zero customer concentration risk They went from 87% revenue dependency on one customer to the most diversified chip company outside Nvidia. In four months. The lesson? Smart money doesn't follow headlines. It follows where the AI leaders are actually spending. OpenAI didn't announce this deal for publicity. They need Cerebras hardware to scale ChatGPT. That's a $10 billion vote of confidence. While everyone's watching Nvidia stock, the real war is happening in inference. And the company with ONE giant chip just beat the company with thousands of tiny ones. What do you think happens when Cerebras IPOs?

MEET THE NVIDIA KILLER: OpenAI bet $10 BILLION on this company that makes chips 20x faster than Nvidia's. If this plays out as expected, it’s over for Nvidia. Cerebras Systems just locked in 750 megawatts of computing power to OpenAI through 2028. For reference: that's equivalent to the annual power consumption of 600,000 US homes. The deal? Over $10 billion. Here's what nobody understands: Cerebras doesn't make normal chips. Nvidia sells you thousands of tiny chips that you connect together. Cerebras makes ONE chip. A single wafer-scale processor the size of a dinner plate. 900,000 AI cores. 4 trillion transistors. All on one piece of silicon. The result? When OpenAI tested it, Cerebras ran inference 20X FASTER than Nvidia GPUs. That's not incremental improvement. That's a different category of performance. But here's where the story gets wild: Four months ago, Cerebras was a struggling company. Their IPO filing revealed that 87% of their revenue came from ONE customer: G42, a UAE-based AI firm. The US government launched a national security review. G42 had ties to Huawei. Ties to China. The IPO collapsed. Investors panicked. Cerebras withdrew their filing in October 2025. Most startups would've been dead. Instead, Cerebras did the opposite. They raised $1.1 billion at an $8.1 billion valuation. Kicked G42 out of the cap table entirely. Got CFIUS clearance. Then landed the OpenAI deal. Now they're raising ANOTHER $1 billion at a $22 billion valuation. They more than DOUBLED their valuation in 4 months. From near-death to $22 billion. While getting rid of their biggest customer. Why OpenAI chose them: ChatGPT has 900 million weekly users. Sam Altman keeps saying they have a "severe shortage" of compute. They need SPEED, not just power. When you ask ChatGPT a question, there's a loop happening: You send request → model thinks → sends response back Nvidia chips are fast at training models. Cerebras chips are built specifically for inference. For real-time responses. For the exact bottleneck OpenAI is trying to solve. Sachin Katti from OpenAI said it best: "Cerebras adds a dedicated low-latency inference solution to our platform. That means faster responses, more natural interactions, and a stronger foundation to scale real-time AI to many more people." In other words: "We need this to scale ChatGPT." The competitive landscape just shifted: Nvidia announced a $100 billion deal with OpenAI in September. But it's still not finalized. Meanwhile, Cerebras closed their deal before Thanksgiving. And it's ALREADY being deployed. Here's the part that should terrify Nvidia: In December, Nvidia bought Groq for $20 billion. Groq makes fast inference chips. Just like Cerebras. So why would Nvidia spend $20 billion buying a competitor to something they supposedly already dominate? Because they know what's coming. Inference is the new battleground. And Cerebras is winning it. The IPO is coming Q2 2026. After this OpenAI deal, Cerebras now has: ✓ IBM contracts ✓ Department of Energy contracts ✓ OpenAI locked in for 3 years ✓ $22 billion valuation ✓ CFIUS clearance ✓ Zero customer concentration risk They went from 87% revenue dependency on one customer to the most diversified chip company outside Nvidia. In four months. The lesson? Smart money doesn't follow headlines. It follows where the AI leaders are actually spending. OpenAI didn't announce this deal for publicity. They need Cerebras hardware to scale ChatGPT. That's a $10 billion vote of confidence. While everyone's watching Nvidia stock, the real war is happening in inference. And the company with ONE giant chip just beat the company with thousands of tiny ones. What do you think happens when Cerebras IPOs?

Ricardo

28,088 views • 6 months ago

After 8+ years on the Tesla Autopilot team and 3 years at Intel, I started Apex Compute to design a new architecture for efficient AI inference. For the past 9 months, we’ve been building our custom inference accelerator. Today we’re releasing Unified Engine v1. Last June we raised our seed round with Maxitech , DeepFin Research, Soma Capital and an incredible group of angel investors. In less than 9 months, we completed our RTL architecture and brought our first pre-silicon prototype to life on FPGA. Our architecture combines systolic array and vector processing in a single compute engine with multiple architectural optimizations, achieving very high FLOPs utilization. A single engine is super lean and it uses less than 90K LUTs and 1 MB Block RAM. It may also be one of the smallest logic-footprint compute engines developed so far. Our Unified Engine v1 supports: -matrix-matrix multiplication (~95% FLOPs utilization) -softmax (~90% FLOPs utilization) -broadcast and element-wise operations -RMSNorm / LayerNorm -block quantization/dequantization (fp4, int4) -multi-engine synchronization and many other operations. We even implemented memory-efficient attention similar to FlashAttention, reaching ~90% FLOP utilization. Full benchmarks and the software stack are available on our GitHub: We have basic compiler written in Python and it supports PyTorch tensors directly to easily test and transfer tensors between the accelerator and host using bf16, fp4 and int4 formats. Our FPGA prototype can already run LLM inference and outperform NVIDIA Jetson Orin Nano, even on a mid-tier FPGA setup (6.4x lower memory bandwidth, 18% slower clock speed at 4.5 Watts). Check the side-by-side comparison video below. Our GitHub includes low-level operator implementations, examples for tiled matrix multiplication, operation chaining, tensor parallelism, attention kernel and a full Gemma 3 1B model implementation. Many more models(Vision Transformers and VLA) are coming soon. Our accelerator IP is AXI-ready for deployment on any AMD(Xilinx) FPGA platform today. Even better, our two-engine prototype runs on an entry-level AMD(Xilinx) FPGA as a PCIe accelerator card. You can purchase it here for $50 to experiment our pre-silicon prototype on your desktop PC or Raspberry Pi 5. We will be releasing hardware bitstream updates as the architecture gets new features. More to come soon! We are expanding our team and looking for compiler engineers and floating-point hardware design engineers. If you're interested, please send me a DM.

After 8+ years on the Tesla Autopilot team and 3 years at Intel, I started Apex Compute to design a new architecture for efficient AI inference. For the past 9 months, we’ve been building our custom inference accelerator. Today we’re releasing Unified Engine v1. Last June we raised our seed round with Maxitech , DeepFin Research, Soma Capital and an incredible group of angel investors. In less than 9 months, we completed our RTL architecture and brought our first pre-silicon prototype to life on FPGA. Our architecture combines systolic array and vector processing in a single compute engine with multiple architectural optimizations, achieving very high FLOPs utilization. A single engine is super lean and it uses less than 90K LUTs and 1 MB Block RAM. It may also be one of the smallest logic-footprint compute engines developed so far. Our Unified Engine v1 supports: -matrix-matrix multiplication (~95% FLOPs utilization) -softmax (~90% FLOPs utilization) -broadcast and element-wise operations -RMSNorm / LayerNorm -block quantization/dequantization (fp4, int4) -multi-engine synchronization and many other operations. We even implemented memory-efficient attention similar to FlashAttention, reaching ~90% FLOP utilization. Full benchmarks and the software stack are available on our GitHub: We have basic compiler written in Python and it supports PyTorch tensors directly to easily test and transfer tensors between the accelerator and host using bf16, fp4 and int4 formats. Our FPGA prototype can already run LLM inference and outperform NVIDIA Jetson Orin Nano, even on a mid-tier FPGA setup (6.4x lower memory bandwidth, 18% slower clock speed at 4.5 Watts). Check the side-by-side comparison video below. Our GitHub includes low-level operator implementations, examples for tiled matrix multiplication, operation chaining, tensor parallelism, attention kernel and a full Gemma 3 1B model implementation. Many more models(Vision Transformers and VLA) are coming soon. Our accelerator IP is AXI-ready for deployment on any AMD(Xilinx) FPGA platform today. Even better, our two-engine prototype runs on an entry-level AMD(Xilinx) FPGA as a PCIe accelerator card. You can purchase it here for $50 to experiment our pre-silicon prototype on your desktop PC or Raspberry Pi 5. We will be releasing hardware bitstream updates as the architecture gets new features. More to come soon! We are expanding our team and looking for compiler engineers and floating-point hardware design engineers. If you're interested, please send me a DM.

Hasan

37,648 views • 5 months ago