hipfire 0.4.5 turns on the copy lane for Strix Halo and R9700 and adds KRAFTON's Raon-1-mini-preview
The Rust inference engine for AMD GPUs reports faster code edits on Strix Halo, native MTP on the 7900 XTX and Raon-1-mini-preview support.
Topic · 6 stories
6 stories tagged amd on AI Tamer, newest first.
The Rust inference engine for AMD GPUs reports faster code edits on Strix Halo, native MTP on the 7900 XTX and Raon-1-mini-preview support.
hipfire 0.4.3 adds a new mq4rs quant for Qwen3.6-35B-A3B with much faster prefill on gfx1201. 0.4.3.1 fixes a 27B MTP load bug and lifts decode about 48%.
warpfront tagged hipfire 0.4.2 and a same-day 0.4.2.1 patch. The notes add a Strix Halo NPU trunk, opt-in expert parallel, and a calibration fix.
At the OCP summit in San Jose, NVIDIA and AMD each described a rack for AI agents, apart from GPU inference. Both are designs and plans, not shipping tests.
Magnitude is an Apache-2.0 on-device inference engine for local agents: desktop app plus magnitude CLI, on-hardware kernel compile and tune, shared prefix cache, one-click agents or an OpenAI-compatible API.
warpfront tagged hipfire v0.4.0 (2026-09-30): Rust LLM inference over HIP kernels for AMD RDNA. Self-reported ≈5,120 tok/s pp8192 on R9700; Qwen3.8-Flash-Next full 262K on one R9700. Serve defaults to 127.0.0.1. Apache-2.0 (residual MIT files).