cd /news/machine-learning/ktransformers-0-7-expands-avx-512-su… · home topics machine-learning article
[ARTICLE · art-100149] src=phoronix.com ↗ pub= topic=machine-learning verified=true sentiment=· neutral

KTransformers 0.7 Expands AVX-512 Support to Benefit AMD EPYC Servers

KTransformers 0.7, the heterogeneous LLM inference and fine-tuning framework, is now available with full AVX-512 support for LoRA fine-tuning that no longer requires Advanced Matrix Extensions (AMX), benefiting AMD EPYC Zen 4, Zen 5, and Zen 6 servers and older Intel Xeon processors. The release also adds VLM fine-tuning support, native FP8 LoRA support, improved DeepSeek V4 deployment, and CPU activation reuse.

read1 min views6 publishedAug 17, 2026
KTransformers 0.7 Expands AVX-512 Support to Benefit AMD EPYC Servers
Image: Phoronix (auto-discovered)

KTransformers as the framework for heterogeneous LLM inference and fine-tune optimizations is out today with its v0.7 feature release.

With KTransformers 0.7 there is now full

The

KTransformers 0.7 also adds VLM fine-tuning support, native FP8 LoRA support, improved DeepSeek V4 deployment, and CPU activation reuse.

More details on KTransformers 0.7 for those using it for LLM inference optimizations and fine-tuning can find all the details via the release announcement on

With KTransformers 0.7 there is now full

AVX-512support for LoRA fine-tuning without depending upon Advanced Matrix Extensions (AMX) also being present. This AVX-512-only without AMX benefits AMD EPYC Zen 4 / Zen 5 / Zen 6 servers with excellent AVX-512 support while lacking AMX and also older Intel Xeon processors with AVX-512 prior to the introduction of AMX with Sapphire Rapids.The

merge requestnoted the testing on AMD hardware and the foxus on AVX-512 without AMX platforms. The KTransformers runtime will automatically select the proper CPU implementation and in turn allowing MoE expert training to happen on a wider range of large-memory servers.KTransformers 0.7 also adds VLM fine-tuning support, native FP8 LoRA support, improved DeepSeek V4 deployment, and CPU activation reuse.

More details on KTransformers 0.7 for those using it for LLM inference optimizations and fine-tuning can find all the details via the release announcement on

── more in #machine-learning 4 stories · sorted by recency
── more on @ktransformers 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/ktransformers-0-7-ex…] indexed:0 read:1min 2026-08-17 ·