Inception has released Mercury 2.5, an update to its diffusion-based language model that the company says is 40% more intelligent than Mercury 2 while keeping the same low-latency, low-cost performance. The model runs at over 1,100 tokens per second on standard NVIDIA GPUs, supports a 260K-token context window, and launches at an 80% discount, priced at $0.04 per million input tokens and $0.15 per million output tokens.
inceptionlabs.ai
· 2026-09-08
AMD published results from experiments running speculative decoding in vLLM on its MI300X and MI355X Instinct GPUs using the ROCm software stack. The team compared five drafting approaches—native MTP, Gemma 4 MTP, EAGLE-3, DFlash, and DSpark—which differ in how draft tokens are generated and how they receive signals from the target model.
vllm.ai
· 2026-09-07
Jon Peddie Research found standalone GPU shipments rose 12.2% quarter over quarter and 14.1% year over year in Q2, even as the broader client CPU market shrank 1.1% annually and desktop PC demand softened. Total consumer PC GPU shipments, including integrated graphics, hit 75.5 million units, with notebook GPU shipments up 16.8% while desktop GPU shipments dropped 4%. Intel led the overall GPU market with 56% share from integrated graphics, followed by Nvidia at 23% and AMD at 21%.
techspot.com
· 2026-09-06
Nvidia has released Personal AI Router (PAIR), a free open-source tool that finds compatible computers on a home network and links them together to run local AI inference tasks through apps like Ollama and LM Studio. It supports Nvidia RTX 20-series and newer GPUs, RTX Pro and DGX Spark systems, plus Apple M4 chips or later, and only taps machines when they're idle so it doesn't interfere with other use.
theverge.com
· 2026-09-03
The Wall Street Journal reported that Nvidia had frozen some transactions under its two-month-old 'take or pay' AI Compute Partnership after partners objected to Nvidia dictating which customers could lease its GPUs. Nvidia pushed back, saying the program remains active and is simply evolving amid strong demand, without confirming or denying specific paused deals.
tomshardware.com
· 2026-08-28
GoKawiil