Topic · 26 stories · page 1 of 2
26 stories tagged nvidia on AI Tamer, newest first.
Open Linux modules lift GeForce FP16 and BF16 tensor issue rates toward 2x on RTX 30 and 40 cards. Owners report 14 to 36% faster LLM prefill, not decode.
Dynamo 1.6.0 adds pluggable router queues, multi-replica Rust EPP and coding-agent session routing. One default change touches Claude Code traffic.
One developer rewrote NVIDIA's streaming RE-USE model in Rust and measured 8.4 ms per 20 ms frame on an M3 CPU, against 16.9 ms through WebGPU.
NVIDIA's Kumo Relational reads linked tables and predicts from up to 10,000 examples in context. Open weights under OpenMDW; benchmarks are NVIDIA's.
NVIDIA posted Flare, an Apache-2.0 local inference server for SM120/SM121 GPUs such as DGX Spark. Python prepares each model; a Rust runtime serves it.
Flora's segmenter, captioner and rewarder are on Hugging Face under a noncommercial license. NVIDIA's ~125x cost edge rests on an assumed GPU price.
Five open NVIDIA retrieval models search page images and text, rerank results and parse PDFs, under the permissive OpenMDW license. What to check first.
Modal's first Vera CPU server matched x86 on quiet single tasks but kept its pace as sandboxes piled up, doubling throughput in Modal's own early benchmark.
DeepInfer is Apache-2.0 and runs V4.1-Flash on NVIDIA SM100 or Huawei Ascend 950. This release is offline inference only, without KV cache or load balancing.
NVIDIA App 11.0.9.565 runs a local MCP server so AI agents can launch games and change settings. VideoCardz found it on by default. One toggle disables it.
NVIDIA's 16 October cards publish Dory 1.0 4B, a looped model with a 256K context, in BF16, MXFP8, NVFP4, and GGUF.
NVIDIA's 15 October posts release open-weight Nemotron 3.5 Super VL and Bolt. The 5x throughput line and partner figures are NVIDIA's.
NVIDIA's 13 October post says Run:ai is open source under DSX. The platform and its component repositories are under Apache 2.0.
NVIDIA and Tri Dao's lab describe ReplaySSM, which caches recent SSM inputs instead of writing full state every step. The speedups are the authors' benchmarks.
At the OCP summit in San Jose, NVIDIA and AMD each described a rack for AI agents, apart from GPU inference. Both are designs and plans, not shipping tests.
NVIDIA Labs' Sol-Engine page describes StreamRender-H3: a code game engine paints semantic maps, and a two-step MiniMax-H3 model renders video. The timings are the page's own.
MIG cuts a supported NVIDIA GPU into up to seven instances with their own memory, cache and compute. How to create them and pick a profile for a model server.
NVIDIA's open-source Boro is a Rust CLI for AI-assisted Linux kernel review, backports and build-boot-test runs before a series goes public. Its LPC 2026 talk asks what could fold into Sashiko.
NVIDIA's bulletin rates CVE-2026-47483 at 8.2: unauthenticated pprof requests can exhaust DCGM Exporter. Lava found about 2,100 hosts exposing exporter metrics. NVIDIA lists 4.8.2 as the fix.
Amazon's October posts describe an open-source physical AI toolchain on AWS, wired to NVIDIA Isaac and Cosmos. The sample repo is Apache-2.0, and its status table still marks edge deployment planned.
At its 8 October science summit, the White House said 11 companies pledged $2.4 billion in compute credits and science tools to the Genesis Mission, led by NVIDIA at $1 billion and AMD at $500 million.
Microsoft opened pre-orders on 7 October for Surface Laptop Ultra at $2,599.99 and the RTX Spark Dev Box from $5,999.99. Laptop Ultra availability starts 16 October.
NVIDIA says a Nemotron coding system scored 535.4 of 600 at IOI 2026 and a math system scored 30 of 42 at IMO 2026. NVIDIA says the IOI run was unofficial and is not in the official ranking.
Magnitude is an Apache-2.0 on-device inference engine for local agents: desktop app plus magnitude CLI, on-hardware kernel compile and tune, shared prefix cache, one-click agents or an OpenAI-compatible API.
