Elektrine
Log in Register

#gpu

38 posts · Last used 3d

Back to Timeline
unwirehk_mirror
UNWIRE.HK @unwirehk_mirror@mastodon.hongkongers.net · 3d ago
TVB 進軍 AI 算力中心 提供人工智能算力服務 擬向外部租用 GPU 無綫集團宣布擬與基滙資本合組公司，於將軍澳電視城園區興建算力設施，採購 GPU 及 CPU 等硬件，向外部客戶 […] #人工智能 #新科創業 #智慧城市 #GPU https://unwire.hk/2026/08/11/tvb-gaw-capital-ai-computing/unwire-space/?utm_source=rss&utm_medium=rss&utm_campaign=tvb-gaw-capital-ai-computing
0
0
0
Dendrobatus_Azureus
Dendrobatus Azureus @Dendrobatus_Azureus@mastodon.bsd.cafe · Aug 02, 2026
This is how we are cheated of our RAM SSD and HDD components by corporate thiefs https://www.youtube.com/watch?v=Eo5w2S-h5dI #LLM #hallucinated #AI #Slop #RAM #GPU #DDR #DDR5 #DDR7 #theft #TV #no
2
0
4
jti42
JTI @jti42@infosec.exchange · Jul 30, 2026
Quite impressive and detailed pictures of recent GPU hardware. https://www.servethehome.com/asrock-rack-4u16x-gnr2-nvidia-hgx-b300-8-gpu-server-intel-zutacore-review/ Especially the later pages have details on the GPU tray. Looks more like you'll need a plumber for maintenance too... :blobwink: #ai #llm #AsrockRack #gpu
1
0
2
BuySellRam
BuySellRam.com @BuySellRam@mstdn.business · Jul 25, 2026
Two years ago an H100 was almost impossible to rent. Now cloud H100s list near $4 per GPU-hour, and used hardware has fallen just as hard. So which is cheaper, renting or owning? It comes down to utilization. A used 8-GPU H100 server can pay for itself in about 8 months at full load, but not for years if it sits at 30%. And resale value, which most comparisons skip... https://www.buysellram.com/blog/cloud-h100s-rent-for-4-an-hour-now-does-owning-gpus-still-pay/ #GPU #H100 #NVIDIA #CloudComputing #MachineLearning #DataCenter #ITAD #GPUcloud #AIhardware
0
0
0
TomAoki @TomAoki@mastodon.bsd.cafe · Jul 21, 2026
Oops! Overlooked new NFB of #NVIDIA #GPU #drivers 610.43.03 (previous one was 610.43."02"!) for 2 weeks... Filed Bug296950 for upgrading -devel variants https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=296950 and opened corresponding review D58375 for #FreeBSD #ports. https://reviews.freebsd.org/D58375 Anyway, seems to be a minor upgrade. https://www.nvidia.com/en-us/drivers/details/274185/ Same Release Highlights for Linux counterpart. https://www.nvidia.com/en-us/drivers/details/274183/
4
0
1
fox
Fox Ritch :fjoxicon:🇩🇪 @fox@social.hostnetwork.xyz · Jul 19, 2026
my 1080ti went to 2ghz and i lost remote connection to it and i lowkey though i crashed my gpu #gpu #gaming #vdi #overclocking
0
0
0
niconiconi @niconiconi@mk.absturztau.be · Oct 28, 2023
New blog post: All GB/s without FLOPS - Nvidia CMP 170HX Review, Performance Lockdown Workaround, Teardown, Watercooling, and Repair https://niconiconi.neocities.org/tech-notes/nvidia-cmp-170hx-review/ #hpc #gpu
0
7
0
niconiconi @niconiconi@mk.absturztau.be · Jul 17, 2026
Replying to @niconiconi@mk.absturztau.be
It's official, the CMP 170HX performance has been unlocked to the Nvidia A100 level by a firmware exploit! 🚀 The community research basically started since three years ago after I publicly tested and reported this card in my blog post. I couldn't hack this card, but "a single spark can start a prairie fire." https://zenodo.org/records/20916112 PoC (mirror): https://github.com/fulracoco/cmpunlocker #hpc #gpu
0
2
0
vulkan
Vulkan @vulkan@fosstodon.org · Jul 16, 2026

Stop guessing at barriers. Start reasoning about dependencies.

Vulkan's hardest topic, rebuilt around the modern standard. This series replaces legacy 1.0 barrier soup with vk::DependencyInfo and timeline semaphores, then uses that foundation to architect an engine-grade frame loop.

https://docs.vulkan.org/tutorial/latest/Synchronization/introduction.html #vulkan #gpu #cpu #synchronization

4
0
2
ros
Rost Glukhov @ros@techhub.social · Jul 13, 2026
Compare NVIDIA Blackwell, AMD Radeon AI Pro R9700, and Intel Arc Pro B70 for local LLM inference. VRAM, bandwidth, software ecosystem, and real-world recommendations. #GPU #AI #NVIDIA #Hardware #infrastructure #LLM #SelfHosting https://www.glukhov.org/hardware/ai/gpu-comparison-ai-workloads-2026-nvidia-amd-intel/
0
1
3
BuySellRam
BuySellRam.com @BuySellRam@mstdn.business · Jul 11, 2026
The cheaper AI tokens get, the more expensive memory becomes. Inference costs fell 280-fold in two years; enterprise AI spending tripled anyway, and DRAM contract prices just posted a record 90-95% quarterly jump. Jevons saw this pattern in 1865 with coal. A look at what actually rebalances the chip market... https://www.buysellram.com/blog/cheaper-tokens-ai-chip-shortage/ #AI #Semiconductors #DRAM #MemoryShortage #DataCenters #HBM #GPU #SSD #ITAD #BuySellRam #JevonsParadox #TechHardware
1
0
1
jimbsr
BuySellRam.com @jimbsr@mastodon.social · Jul 11, 2026
The cheaper AI tokens get, the more expensive memory becomes. Inference costs fell 280-fold in two years; enterprise AI spending tripled anyway, and DRAM contract prices just posted a record 90-95% quarterly jump. Jevons saw this pattern in 1865 with coal. A look at what actually rebalances the chip market... https://www.buysellram.com/blog/cheaper-tokens-ai-chip-shortage/ #AI #Semiconductors #DRAM #MemoryShortage #DataCenters #HBM #GPU #SSD #ITAD #BuySellRam #JevonsParadox #TechHardware #tech
2
0
2
fox
Fox Ritch :fjoxicon:🇩🇪 @fox@social.hostnetwork.xyz · Jul 06, 2026
so i tried to make a nested proxmox vgpu thingy. but it doesnt work cause when i enabled viommu on the vm the nvidia driver fails(RmInitAdapter failed) but when i disable viommu mdev doesnt work cause it needs /sys/kernel/iommu_groups/ which only exsists with iommu. i fucking hate this bullshit. #proxmox #vgpu #viommu #iommu #gpu #nvidia #server #homelab #selfhosting #vm #qemu #pciepassthrough #mdev
0
0
0