Install
CUDA & Compute
CUDA, creator workloads, AI frameworks, and encoder/decoder blocks.
- 17 Tracked terms
- Last 30 days Feed window
What this topic collects on
An article joins this feed when it matches these terms. Each one is also a search of its own.
Related topics
Latest in CUDA & Compute
ASUS’s “DGX Spark’ Ascent GX10 will get 64GB version targeting 30-35B class models
18+ hour, 23+ min ago (271+ words) Tech Critter ASUS has announced it will be shipping the Ascent GX10 with 64GB of memory, joining the existing 128GB variant for more flexibility when it comes to shopping for local AI machines. The 64GB version uses the same NVIDIA GB10 Grace Blackwell Superchip as…...
Machine Learning in PHP: Rubix ML + Tensor Extension on a Single-Core EPYC
12+ hour, 44+ min ago (333+ words) Running Rubix ML with the Tensor extension on a single-core AMD EPYC, 1 GB RAM VPS, we achieved production-grade ML performance: mikrosaniye-level inference, 1. Why This Matters PHP is dismissed as “just a web language.” That’s outdated. With Rubix ML and the…...
Why is Speculative Decoding Fast?
3+ day, 23+ hour ago (722+ words) It's not because you do less work. It's because you change the kind of work the GPU is doing. There is a common misconception that speculative decoding is fast because you do less work per token. That just “verifying” a…...
What I Learned by Dissecting gemma-4-E2B-it_qualcomm_sm8750.litertlm
17+ hour, 29+ min ago (910+ words) Gemma 4 Challenge: Write about Gemma 4 Submission I recently started exploring on-device AI inference, and honestly, the initial experience was overwhelming. Hundreds of models on HuggingFace, unfamiliar architecture names, quantization formats, chip-specific variants - it felt like drinking from a firehose. When…...
My Fine-Tuned Gemma 4 Loaded Fine, Then Broke on the First Message
17+ hour, 29+ min ago (743+ words) I fine-tuned Gemma 4 E2B. The adapter merged cleanly. The export to.litertlm completed without errors. I pushed the model to my phone, initialized the engine, and everything looked green. Then I tried to create a conversation and got this: No model…...
Nvidia's Vera CPU Packs a 1K-Entry Reorder Buffer in Its Custom Olympus Core
18+ hour, 16+ min ago (865+ words) Nvidia revealed its custom Olympus CPU core at Hot Chips, detailing a Vera processor with a reorder buffer exceeding 1,000 entries, 16-instruction-per-cycle fetch, and 18 issue ports. The design splits the pipeline into front end, mid core, and back end, with the…...
4-bit GGUF Quality for MoE Models: Why Only 3B of 180B Params Fire, and How to Prove Parity
18+ hour, 38+ min ago (944+ words) The practical consequence: the "180B" headline counts total parameters, while the compute and the active memory traffic track the much smaller active set, on the order of 3B. Two numbers describe an MoE and they answer different questions: Quantization touches storage, so…...
New FFT Library Pushes Four-Dimensional Transforms Across Multi-GPU Supercomputers
18+ hour, 46+ min ago (640+ words) A new open-source C++ library called FFTM brings portable distributed 3D and 4D fast Fourier transforms to CUDA and HIP multi-GPU systems, with autotuning and strong scaling results on up to 120 A100 GPUs....
Gemma 4 26B A4B vs Gemma 4 E4B: Benchmarks & Cost
2+ day, 22+ hour ago (388+ words) Updated October 10, 2026. Rank says Gemma 4 26B A4B is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty. This is a same-family comparison, so migration details appear when the source data supports them. Gemma 4 26B A4B vs…...
Gemma 4 26B A4B vs Gemma 4 E2B: Benchmarks & Cost
2+ day, 22+ hour ago (388+ words) Updated October 10, 2026. Rank says Gemma 4 26B A4B is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty. This is a same-family comparison, so migration details appear when the source data supports them. Gemma 4 26B A4B vs…...