PulseAugur
EN
LIVE 18:09:08

AMD code now upstreamed into NVIDIA's NIXL library after 10-year block · 6 sources tracked

By PulseAugur Editorial · [6 sources] ·

SemiAnalysis reports that AMD engineers can now directly contribute code changes to NVIDIA's NIXL Inference communication library. This development follows a decade-long period where NVIDIA largely prevented AMD from upstreaming its code. Through efforts over the past two years, SemiAnalysis facilitated a reconciliation, leading to NVIDIA accepting AMD's pull requests. This integration, finalized in June 2026, eliminates the need for AMD to maintain a separate fork, saving significant engineering hours. AI

IMPACT This integration streamlines AI development by allowing direct contributions to critical inference libraries, potentially accelerating hardware-software co-optimization.

RANK_REASON Partnership between major competitors AMD and NVIDIA on core AI infrastructure, facilitated by a third party.

Read on X — SemiAnalysis →

AI-generated summary · Google Gemini · from 6 sources. How we write summaries →

AMD code now upstreamed into NVIDIA's NIXL library after 10-year block · 6 sources tracked

COVERAGE [6]

  1. X — SemiAnalysis TIER_1 English(EN) · SemiAnalysis_ ·

    AMD engineers are now landing their code changes directly into NIXL upstream instead of needing to waste dozens of engineering hours every month syncing upstrea

    AMD engineers are now landing their code changes directly into NIXL upstream instead of needing to waste dozens of engineering hours every month syncing upstream into their RIXL fork. 6/6🧵 https://t.co/FiCaq1tJ1c

  2. X — SemiAnalysis TIER_1 English(EN) · SemiAnalysis_ ·

    AMD has now deprecated its fork and is fully supporting upstream NIXL development. 5/6🧵 https://t.co/PWmnqglAkd

    AMD has now deprecated its fork and is fully supporting upstream NIXL development. 5/6🧵 https://t.co/PWmnqglAkd

  3. X — SemiAnalysis TIER_1 English(EN) · SemiAnalysis_ ·

    Thus, in early 2026, we connected AMD's Head of AI Application Engineering, Andy Luo, to the NIXL team, and in June 2026, AMD was finally able to merge its code

    Thus, in early 2026, we connected AMD's Head of AI Application Engineering, Andy Luo, to the NIXL team, and in June 2026, AMD was finally able to merge its code into NVIDIA's libraries. 4/6🧵 https://t.co/qOOqlnY0gD

  4. X — SemiAnalysis TIER_1 English(EN) · SemiAnalysis_ ·

    12 months later, at GTC 2026, during a Dynamo session, we asked again from a different angle:

    12 months later, at GTC 2026, during a Dynamo session, we asked again from a different angle: NIXL had already merged upstream contributions from Trainium's Neuron fork. Would it take them from AMD's RIXL fork? The maintainers said they would, in front of a room. 3/6🧵

  5. X — SemiAnalysis TIER_1 English(EN) · SemiAnalysis_ ·

    At GTC 2025, we asked NVIDIA point-blank: with the big comms library refactor coming, would you help AMD's team adapt their fork?

    At GTC 2025, we asked NVIDIA point-blank: with the big comms library refactor coming, would you help AMD's team adapt their fork? The NVIDIA communication software architect said clearly that NVIDIA doesn't participate in AMD comms development at all. 2/6🧵

  6. X — SemiAnalysis TIER_1 English(EN) · SemiAnalysis_ ·

    For the past 10 years, NVIDIA prevented AMD from upstreaming its code into NVIDIA’s libraries, but over the past 24 months, SemiAnalysis has squashed the beef,

    For the past 10 years, NVIDIA prevented AMD from upstreaming its code into NVIDIA’s libraries, but over the past 24 months, SemiAnalysis has squashed the beef, and NVIDIA has started accepting AMD PRs into the ultra-important NIXL Inference communication library. We explain https…

RELATED ENTITIES

RELATED TOPICS