PulseAugur
EN
LIVE 12:25:38

llama.cpp adds OCP FP8 support for NVIDIA GPUs, boosting performance

By PulseAugur Editorial · [1 sources] ·

The llama.cpp project has introduced support for OCP FP8 (Octet-Compressed Precision Floating Point 8-bit) on CUDA, enhancing performance for NVIDIA GPUs. This update includes optimizations for General Matrix Vector Multiplication (GEMV) and integrates FP8 support into FlashAttention and cuBLAS. Benchmarks show significant speedups, particularly with the Qwen3.6-27B-NVFP4 model on an NVIDIA RTX Pro 4500 Blackwell GPU, demonstrating improved inference times. AI

IMPACT Enhances inference speed for large language models on compatible NVIDIA hardware.

RANK_REASON This is a software update for an open-source project that improves performance for specific hardware and models, rather than a new frontier model release or significant industry event.

Read on llama.cpp — Releases →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

llama.cpp adds OCP FP8 support for NVIDIA GPUs, boosting performance

How we ranked this

Signal score
11 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
This is a software update for an open-source project that improves performance for specific hardware and models, rather than a new frontier model release or significant industry event.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
infra, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. llama.cpp — Releases TIER_1 English(EN) · ORippler ·

    b12284: CUDA: Add OCP FP8 support (#28413)

    <ul> <li> <p>Initial CUDA WIP version</p> </li> <li> <p>Use fp8 intrinsics</p> </li> <li> <p>Do W8A16 for FP8 in GEMV case</p> </li> </ul> <p>(base) osimons@ub-osimons:~/lcpp_fp8.git$ ./build-x64-linux-gcc-reldbg/bin/llama-bench -m /mnt/share/gguf/nvidia/Qwen3.6-27B-NVFP4/Qwen3.6…

RELATED ENTITIES

RELATED TOPICS