{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiboz3iio6zoyz2v43r6n22clia7bwrb5nao5l4ogicqhyw34e6hsi",
"uri": "at://did:plc:dgckedirabhiow2v2pwuizex/app.bsky.feed.post/3miixv7gkfvr2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreic2z7enngwclmpw3enizohqfcii2fg77a5kzvwa42n5i5hbltreqe"
},
"mimeType": "image/webp",
"size": 3904
},
"path": "/news/KTransformers-0.5.3",
"publishedAt": "2026-04-02T10:01:56.000Z",
"site": "https://www.phoronix.com",
"textContent": "KTransformers 0.5.3 released today for this framework for efficient inferencing and fine-tuning of large language models (LLMs) with a focus on CPU-GPU heterogeneous computing. With this release, KTransformers 0.5.3 is now more applicable for CPUs lacking Advanced Matrix Extensions (AMX) and AVX-512 in now providing some AVX2-only kernels too...",
"title": "KTransformers Adds AVX2 MoE Support For Viable Performance On CPUs Without AMX/AVX-512"
}