v0.7.0
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cpp11 min read
IBM Research Blog
Stay updated with the latest developments in Artificial Intelligence
Agents on live hardware: reason where you must, engineer everywhere else
CoreWeave Blog10 min read
b11669
llama.cpp1 min read
Preparing chip designers for the nanostack era
IBM is releasing a process design kit for our groundbreaking 0.7-nanometer transistor architecture.
IBM Research Blog3 min read
Scaling AI-driven chip design with open agent factories
Open models and llm-d enabled IBM Research to explore quantum error correction hardware at 11.5× lower inference cost than an all-proprietary configuration.
IBM Research Blog7 min read
How distributed inference keeps large AI models moving
Distributed inference serving is an air traffic control tower for AI traffic, and agentic workflows make it more necessary than ever.
IBM Research Blog12 min read
What's new at IBM Quantum Q3 2026
Explore the latest updates, releases, and resources from IBM Quantum and the Qiskit community.
IBM Research Blog3 min read
Qiskit beyond Python: Fortran, C++, and Julia
Qiskit’s C API connects the SDK’s Rust core to the languages of HPC and scientific computing, so you can build and run circuits natively—no Python required.
IBM Research Blog11 min read
Directed execution: same performance, more control
See, customize, and extend how your circuits use the error mitigation and correction methods researchers are exploring today on IBM quantum hardware
IBM Research Blog15 min read
Ponder This Challenge - October 2026 - The Ultimate Ultimate Tic-Tac-Toe Game
The well-known game of Ultimate Tic-Tac-Toe is played on a 9×99\times 9 board (with the rows and columns numbered by 0,1,…,80,1,\ldots,8), conceptually divided into nine 3×33\times 3 small boards. The players are denoted by "X" and "O" and take turns, starting with X.
IBM Research Blog4 min read
Why are silicon wafers round?
It’s a result of metallurgy, but circular silicon wafers are also the best shape to ensure uniformity in the chip production process.
IBM Research Blog7 min read
From error mitigation to fault-tolerant quantum computing
A spectrum of error-correcting techniques is enabling useful quantum computation, measured not by logical qubits but by the circuits you can run with them.
IBM Research Blog10 min read
A theoretical separation between quantum computers & LLMs
Recent research further demonstrates the theoretical abilities of quantum computing
IBM Research Blog7 min read
Introducing IBM and NASA's new foundation model for the Moon
The multi-modal model could help astronauts navigate craters, investigate ancient lava, and search for ice, as the US plans for a long-term lunar presence.
IBM Research Blog8 min read
Switzerland's first IBM Quantum System Two
Lockheed Martin and IBM are launching a Swiss quantum innovation hub at ETH Zurich to advance research, industry collaboration, and workforce development.
IBM Research Blog6 min read
Cleveland Clinic, RIKEN, IBM named Gordon Bell finalists
Finalist recognition for one of supercomputing’s top prizes arrives as researchers report new progress in automated quantum-HPC chemistry workflows.
IBM Research Blog2 min read
How llm-d makes the most of the hardware you already have
IBM Research and Red Hat deployed a 753B open model on H100 GPUs, serving thousands of concurrent coding agents at 5-10x lower cost than commercial APIs.
IBM Research Blog8 min read
Ponder This Challenge - September 2026 - Loeschian Arithmetic Progressions
In a now-famous 2004 article, Ben Green and Terence Tao proved that arbitrarily long arithmetic progressions exist in the primes. This holds true analogously for other sets of numbers if their density is sufficiently high, for example, numbers that are the sum of two squares.
IBM Research Blog5 min read
IBM Quantum Nighthawk r2—more circuits, faster
High-speed, independent qubit reset boosts circuit throughput 25x over Heron while enabling accurate observable estimation on circuits with 7,500+ gates.
IBM Research Blog7 min read
What happens when information theory accounts for reasoning?
At IBM Research, we’re inventing what’s next in AI, quantum computing, and hybrid cloud to shape the world ahead.
IBM Research Blog5 min read
Granite 4.2 brings native reasoning to enterprise agents
IBM’s new open Granite models are designed for agentic AI, combining reasoning, tool use, coding, instruction following, and speech capabilities.
IBM Research Blog5 min read
Showing 18 of 26 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news from IBM Research Blog
Join 15,000+ AI enthusiasts