Snapdragon 8 Gen 1 (Samsung Foundry 4LPX) vs Snapdragon 8 Gen 1 (TSMC N4) dieshots annotated shot by : b23.tv/H2drEFh

Intel Wildcat Lake Refresh reportedly moves to 8 cores, replacing cancelled 6-core Nova Lake videocardz.com/newz/intel-wi…

I’d like to clarify a few things here: During our conversation, we touched on the topic of FSR 4.1 on RDNA 3, and in that context, it was mentioned that there are currently no plans to implement it on RDNA 3.5.

Sparkle Squeezes Intel's 32 GB Arc Pro B70 Into A Single Slot, Unlocking 256 GB VRAM Workstations wccftech.com/sparkle-squeeze… wccftech.com/sparkle-squeeze…

AMD FSR 4.1 to skip RDNA 3.5 integrated graphics videocardz.com/newz/amd-fsr-…

Welp, i guess no FSR4 on APUs until Medusa

Lmao wtf is Gigabyte doing

Intel's AutoRound post-training quantization is now integrated natively into vLLM-Omni, bringing W4A16 (4-bit) to Omni multimodal, diffusion image, and video models. It cuts Qwen3-Omni-30B from 66GB to 25GB with no quality cliff. Quantize once offline, then serve with the same command as the BF16 model. 📈 Highlights: - weights shrink to ~1/4 of BF16, dropping FLUX.1-dev from 4 GPUs (TP=4) to a single one - accuracy held on OmniBench, with ~1.3% drift on text-to-image - on Intel XPU B60, the freed memory unlocks CFG Parallel for 1.55-1.67x faster guided diffusion 🙌 Thanks to @IntelAI, @HaihaoShen, and the vLLM-Omni team for the collaboration! 🔗 vllm.ai/blog/2026-06-02-vllm…

At @gskillgaming: ➡️ 0.5 TB of RDIMMs (8 x 64 GB) ➡️ Xeon 698X ➡️ DDR5-10000 !!! ➡️ 512-bit bus ➡️ 602 GB/sec read 🤯🤯

Increase performance per watt and enhance efficiency in 5G telco and cloud-native applications. Today, Intel launches #IntelXeon 6 , the first data center CPU built on Intel 18A to help AI go to work. Read the press release: ms.spr.ly/6017vwAGZ

Want a sneak peek of what Intel is bringing to Computex?🚀 AI Playground Home Agent is officially available for early testing in our latest v3.1.1-beta! @intel is bringing AI execution out of the cloud and putting it directly in your control, right from your home hardware. Here is what you can do with it today: 📱 True Remote Access: Connect and run your local AI from any device. 💰 Zero Token Costs: Free, unlimited use without subscription fees. 🛠️ MCP Integration: Local AI access and control for 3rd party Model Context Protocol supported apps. 🎨 All-in-One Creation: Advanced chat, image generation, image editing, and video generation powered by 60 curated open-source models. Intel and our OEM partners will be sharing more details at Computex, but you don't have to wait. 👇 Grab the beta, test it out on your Intel Core Ultra, Arc Graphics, or RTX hardware, and let us know what you think! 🔗 lnkd.in/gf8wp9ZM #AIPlayground #IntelCoreUltra #IntelArc #GenerativeAI #OpenSource #Computex2026 #ModelContextProtocol

Intel: DMR, Crescent island, WCL AMD: FPGAs, MI400 series Nvidia: Vera, Rubin, Spectrum, bluefield and VPU Google, Meta, Microsoft: TPUv8, MTAI 400, MAIA 200 Arm: AGI CPU Fujitsu: Monaka CPU Samsung: LP5X-PIM Sambanova: SN50 Broadcom: Thor ultra IBM: Z and Inference chip

Damn this year's hotchips is packed, so excited for this one

Introducing Intel Arc G3 Extreme processors. Immersive gameplay. Exceptional battery life. No compromise. Next-gen handheld gaming is here. Learn more: ms.spr.ly/6011vZDcW

CPU : 4x C1 Pro 2.6GHz 4x C1 Nano 2GHz Mali G625 MC2 GPU mediatek.com/products/smartp… HOLY FUCK NOT A REBRAND

Exynos 2600 Dieshot Thanks By Geekerwans give chip and money Kurnal Layout Geekerwans Video bilibili.com/video/BV1bwVp67…

Intel to officially announce Arc G3 for gaming handhelds on May 28 videocardz.com/newz/intel-to…

Exclusive: Acer Predator Atlas 8 gaming handheld to feature Arc G3 series videocardz.com/newz/exclusiv…

Some more slides upscaled. The whole presentation seems to be AI generated. And this doesn’t look that much different from what AMD is doing, aka core logic over SRAM/PHY/Analog. Interestingly they are doing 3-layer stacking in Kunpeng 960 with top 2 layer being core logic.

GA100 80G