--- title: KTransformers 0.7 Expands AVX-512 Support To Benefit AMD... description: KTransformers 0.7 adds full AVX-512 support for LoRA fine-tuning that no longer requires Advanced Matrix Extensions (AMX), benefiting AMD EPYC Zen 4/5/6... canonical: https://daily.dev/posts/ktransformers-0-7-expands-avx-512-support-to-benefit-amd-epyc-servers-6vm0qcjy9 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: KTransformers 0.7 Expands AVX-512 Support To Benefit AMD EPYC Servers | daily.dev og:description: KTransformers 0.7 adds full AVX-512 support for LoRA fine-tuning that no longer requires Advanced Matrix Extensions (AMX), benefiting AMD EPYC Zen 4/5/6... og:url: https://daily.dev/posts/ktransformers-0-7-expands-avx-512-support-to-benefit-amd-epyc-servers-6vm0qcjy9 og:image: https://api.daily.dev/og/posts/6VM0qCjY9.png og:image:alt: KTransformers 0.7 Expands AVX-512 Support To Benefit AMD EPYC Servers og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # KTransformers 0.7 Expands AVX-512 Support To Benefit AMD EPYC Servers **[Phoronix](https://daily.dev/sources/phoronix)** · 1 min read · 0 upvotes · 0 comments ## Summary KTransformers 0.7 adds full AVX-512 support for LoRA fine-tuning that no longer requires Advanced Matrix Extensions (AMX), benefiting AMD EPYC Zen 4/5/6 servers and older Intel Xeon CPUs that lack AMX. The runtime automatically picks the correct CPU implementation, widening the range of large-memory servers usable for MoE expert training. The release also brings VLM fine-tuning support, native FP8 LoRA support, improved DeepSeek V4 deployment, and CPU activation reuse. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Does KTransformers support LoRA fine-tuning on AMD EPYC servers without AMX? Yes, KTransformers 0.7 adds full AVX-512 support for LoRA fine-tuning that no longer depends on Advanced Matrix Extensions (AMX) being present. This benefits AMD EPYC Zen 4, Zen 5, and Zen 6 servers, which have strong AVX-512 support but lack AMX, as well as older Intel Xeon processors predating AMX support introduced with Sapphire Rapids. _Track releases like this on daily.dev to stay current on LLM fine-tuning hardware compatibility._ ### What new features does KTransformers 0.7 include besides AVX-512 support? KTransformers 0.7 adds VLM fine-tuning support, native FP8 LoRA support, improved DeepSeek V4 deployment, and CPU activation reuse. The runtime also automatically selects the proper CPU implementation, allowing mixture-of-experts (MoE) training to run on a wider range of large-memory servers. _Developers evaluating inference frameworks can follow updates like these on daily.dev._ ## Similar posts on daily.dev - [KTransformers Adds AVX2 MoE Support For Viable Performance On CPUs Without AMX/AVX-512](https://daily.dev/posts/ktransformers-adds-avx2-moe-support-for-viable-performance-on-cpus-without-amx-avx-512-oh2oy9xmc) · Phoronix · 0 upvotes · 0 comments - [Efficient MoE Pre-training at Scale on 1K AMD GPUs with TorchTitan – PyTorch](https://daily.dev/posts/efficient-moe-pre-training-at-scale-on-1k-amd-gpus-with-torchtitan-pytorch-xscr4vica) · PyTorch · 0 upvotes · 0 comments - [Beyond Porting: How vLLM Orchestrates High-Performance Inference on AMD ROCm](https://daily.dev/posts/beyond-porting-how-vllm-orchestrates-high-performance-inference-on-amd-rocm-9sjfha0v1) · vLLM · 2 upvotes · 0 comments - [AVX-512 Optimization For Linux RAID Showing Up To 41% Improvement On AMD Ryzen 9 9950X](https://daily.dev/posts/avx-512-optimization-for-linux-raid-showing-up-to-41-improvement-on-amd-ryzen-9-9950x-poo478v4o) · Phoronix · 1 upvotes · 0 comments - [Accelerating Dropless MoE Training in JAX with NVIDIA Transformer Engine](https://daily.dev/posts/accelerating-dropless-moe-training-in-jax-with-nvidia-transformer-engine-iqd8saow0) · NVIDIA Developer · 0 upvotes · 0 comments --- Tags: [#ai-inference](https://daily.dev/tags/ai-inference) [View this post on daily.dev](https://daily.dev/posts/ktransformers-0-7-expands-avx-512-support-to-benefit-amd-epyc-servers-6vm0qcjy9) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"KTransformers 0.7 Expands AVX-512 Support To Benefit AMD EPYC Servers","url":"https://daily.dev/posts/ktransformers-0-7-expands-avx-512-support-to-benefit-amd-epyc-servers-6vm0qcjy9","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/ktransformers-0-7-expands-avx-512-support-to-benefit-amd-epyc-servers-6vm0qcjy9"},"datePublished":"2026-08-17T11:31:44.240Z","dateModified":"2026-08-17T11:32:11.661Z","description":"KTransformers 0.7 adds full AVX-512 support for LoRA fine-tuning that no longer requires Advanced Matrix Extensions (AMX), benefiting AMD EPYC Zen 4/5/6...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/cb4a24a72775bf190285a2a157d59306?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/cb4a24a72775bf190285a2a157d59306?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Phoronix","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Phoronix","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/6a26ba379dd64932830aa0c9803dd7ee","url":"https://daily.dev/sources/phoronix"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/ktransformers-0-7-expands-avx-512-support-to-benefit-amd-epyc-servers-6vm0qcjy9","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-inference","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Phoronix","item":"https://daily.dev/sources/phoronix"},{"@type":"ListItem","position":3,"name":"KTransformers 0.7 Expands AVX-512 Support To Benefit AMD EPYC Servers"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/ktransformers-0-7-expands-avx-512-support-to-benefit-amd-epyc-servers-6vm0qcjy9#faq","mainEntity":[{"@type":"Question","name":"Does KTransformers support LoRA fine-tuning on AMD EPYC servers without AMX?","acceptedAnswer":{"@type":"Answer","text":"Yes, KTransformers 0.7 adds full AVX-512 support for LoRA fine-tuning that no longer depends on Advanced Matrix Extensions (AMX) being present. This benefits AMD EPYC Zen 4, Zen 5, and Zen 6 servers, which have strong AVX-512 support but lack AMX, as well as older Intel Xeon processors predating AMX support introduced with Sapphire Rapids. Track releases like this on daily.dev to stay current on LLM fine-tuning hardware compatibility."}},{"@type":"Question","name":"What new features does KTransformers 0.7 include besides AVX-512 support?","acceptedAnswer":{"@type":"Answer","text":"KTransformers 0.7 adds VLM fine-tuning support, native FP8 LoRA support, improved DeepSeek V4 deployment, and CPU activation reuse. The runtime also automatically selects the proper CPU implementation, allowing mixture-of-experts (MoE) training to run on a wider range of large-memory servers. Developers evaluating inference frameworks can follow updates like these on daily.dev."}}]} ```