VLLM - Frontier Models

There are 104 items in this page

01:16:25

News & Opinion2 months ago

Multi-GPU Kernels, Intelligence per Watt, Heterogeneous Inference, and More | YC Paper Club

This YC Paper Club special edition gathers Stanford researchers and senior engineers for a dense technical panel on GPU kernel optimi...

09:16

Coding & Builds2 months ago

DeepSeek V4 Flash Fully Local — 32 tok/s on a Single Chip

Fahd Mirza demonstrates running DeepSeek V4 Flash, a 284-billion parameter mixture-of-experts model, entirely on a single AMD Ryzen A...

09:20

Coding & Builds3 months ago

Nanbeige4.2 – 3B Model That Beats 9B Models | Local Install + Real App Test

Fahd Mirza tests Nanbeige 4.2, the second release from Nan Beach and a 3-billion-parameter model built on a "looped transformer" arch...

08:12

Tutorials3 months ago

Gemma 4 Just Got a Massive Update (Tested Live Locally)

Fahd Mirza puts Gemma 4's latest patch update under the microscope in a live session running on an Nvidia H100 with vLLM on a fresh U...

49:44

Interviews3 months ago

The AI Memory Problem: Why Long Context Isn’t Enough — Dan Biderman, Engram Co-founder & CEO

Dan Biderman, co-founder and CEO of Engram — the AI memory startup that raised a $98 million seed round — joins the Latent Space podc...

08:13

Deep Dives3 months ago

China’s AI Chips: What’s Real and What’s Just a Slide

Fahd Mirza cuts through the hype around China's AI chip industry, offering a technically grounded breakdown of what current domestic...

13:00

Coding & Builds3 months ago

Tess-4-27B + EAGLE-3: Local Reasoning, Nearly 2× Faster

Fahd Mirza demonstrates running Tess-4-27B — a reasoning-capable fine-tune of Qwen 3.6 27B by Miguel de Icaza — locally on an NVIDIA...

09:19

Coding & Builds3 months ago

Lift: Schema-Based PDF Extraction Tested Locally on 10 Languages

Fahd Mirza tests Lift, a 9-billion parameter model purpose-built for schema-constrained PDF extraction, deployed locally on Ubuntu wi...

08:08

Reviews & Comparisons3 months ago

$2000 96GB Huawei GPU vs Nvidia — Is This The End of the Monopoly?

Fahd Mirza investigates the Huawei Atlas 300I Duo — a 96 GB AI accelerator currently listed on Alibaba for $2,600–$2,800 — which has...

11:07

Coding & Builds3 months ago

NVIDIA Puzzle 75B: A 120B Model Squeezed onto ONE GPU

NVIDIA's Nemotron Lab 3 Puzzle 75B compresses the 120B-parameter Nemotron Super model down to 75B total parameters — with only 9.3B a...