» Tag
gpu
82 posts397B MoE Model Runs on a Single RTX PRO 6000 96GB GPU
Krasis runtime runs a 397B-parameter MoE model on one RTX PRO 6000 96GB GPU, hitting 2,354 tok/s prefill via CPU-VRAM expert streaming.
Reverse-Engineering Nvidia B200's Tensor Core Down to the Bit
Engineers reverse-engineered Nvidia B200's tcgen05.mma tensor core, releasing a bit-exact open-source model revealing its hidden fixed-point accumulation.
metaljax Brings Unmodified JAX Code to Apple Silicon GPUs
metaljax is an open-source PJRT plugin running JAX on Apple Silicon GPUs via MLX, passing 98.4% of JAX's official test suite in beta.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comFaCTz: GPU Compressor Preserves Vector-Field Topology at 60 GB/s
FaCTz is the first GPU-based lossy compressor guaranteeing critical-point preservation in vector fields, hitting 60 GB/s—up to 640x faster than cpSZ.
LoRA Speedrun: A Public Wall-Clock Leaderboard for Fine-Tuning
LoRA Speedrun is a public, verified wall-clock leaderboard for LoRA fine-tuning techniques on Qwen2.5-1.5B and GSM8K, run on a single L40S GPU.
How We Self-Host DeepSeek V4 Flash on AWS Spot Instances
Inside a self-hosted DeepSeek V4 Flash deployment on AWS spot GPUs: MXFP4 quantization, RTX PRO 6000 hardware, DSpark decoding, and KV cache tuning.
The Real Cost of LLM Inference Is Memory Bandwidth
LLM serving costs are driven by memory bandwidth, not FLOPs. Why KV cache movement, prefill/decode disaggregation, and batching define real inference economics.
NVIDIA ModelExpress: P2P RDMA Cuts Model Startup From Minutes to Seconds
NVIDIA ModelExpress speeds up LLM weight loading with P2P GPU-to-GPU RDMA transfers, cutting model startup time from minutes to seconds.
GoCL: A Zero-Overhead C++20 Vulkan Proxy Layer
GoCL is an open-source C++20 Vulkan proxy that rewrites SPIR-V on the fly based on GPU capabilities, lazy-loads heavy backends, and adds zero measurable runtime overhead.
Linux 7.2 Released with Cache-Aware Scheduler and USB4STREAM
Linux 7.2 ships cache-aware task scheduling, a fairer GPU scheduler, USB4STREAM support, and Btrfs performance gains.