A developer built zipgate, an MIT-licensed Python tool that hand-parses ZIP local file headers and central directory entries to detect malformed ZIP64 extra fields (0x0001) that Python's zipfile silen…
AMD demonstrated that Ai2's open-source MolmoAct2 vision-language-action model can run entirely on a single AMD Ryzen AI Max+ 395 "Strix Halo" mini PC using the ROCm software stack, with no cloud or e…
A developer documented a method for installing AMD's ROCm 10 on Fedora using the vendor's TheRock tarball, which bypasses the OS check that blocks Fedora in AMD's runfile and dnf repositories. The set…
AMD VP of Software Anush Elangovan said agentic AI is drastically lowering the barrier to entry for low-level hardware programming, in a discussion about ROCm, AMD's unified open-source software layer…
A developer released two open-source Python tools aimed at simplifying local LLM inference on AMD GPUs. ROCmFix automatically resolves HSA_OVERRIDE_GFX_VERSION issues by querying PCI IDs via the Windo…
A developer released gemmcheck3, a self-checking rocBLAS GEMM stress test for AMD GPUs targeting RDNA3/gfx11 hardware such as the RX 7900 XTX. The tool runs five rocblas_gemm_ex calls in LLM layer sha…
A user request asks that the AMD Radeon AI PRO R9700 be added to the "My Hardware" database, citing its RDNA4 architecture, 32 GB GDDR6 memory, and 383 FP8 TFLOPS / 383 INT8 TOPS throughput as making …
A developer published a step-by-step guide and open-source MCP toolkit for deploying Google's Gemma 4 E2B model to a single AMD Instinct MI300X GPU rented through AMD Developer Cloud at $1.99 per hour…
A developer built a suite of twelve tag-scoped MCP tools to inventory and manage a single AMD Instinct MI300X GPU on AMD Developer Cloud, using the same server to read the card's native numeric format…
AMD published a step-by-step recipe for reproducing its MLPerf Inference v6.1 submission results on AMD Instinct MI355X, MI350X, and MI350P GPUs, marking the company's fifth consecutive round of MLPer…
A developer published a troubleshooting guide explaining how to diagnose why Ollama falls back to CPU inference instead of using a GPU on Linux, Windows, and WSL. The guide centers on the `ollama ps` …
A developer published an initial provisioning specification and compose templates on GitHub for running local LLMs, Open WebUI, and dev agents in isolated rootless containers with direct GPU accelerat…
DFlash, a block-diffusion speculative decoding drafter, delivered up to 5.02× single-request throughput on Qwen3.5-27B when run on AMD Instinct MI355X through vLLM on ROCm, according to the benchmark.…
Salvatore Sanfilippo (antirez) announced that Qwen3.8 Flash Next is now supported in DwarfStar, delivering 50–70 tokens per second inference and over 1400 tokens per second prefill on 64GB Mac systems…
A GitHub project called "CUDA for AMD on Windows," built by a developer going by "speed," packages the ZLUDA translation layer with AMD's HIP SDK and ROCm to run unmodified CUDA applications on AMD GP…
A reproducible Windows CUDA compatibility stack built on ZLUDA v6-preview.69 and AMD HIP SDK 6.4 has been published on GitHub, validated only on the AMD Radeon RX 9060 XT (gfx1200). The setup passes c…
A fine-tuned Qwen2.5-Coder-14B-Instruct model compiled 170 of 184 MQL5 test prompts after one epoch of training on the author's dataset, up from 2 of 184 for the untouched base model, according to a p…
A 2026 guide compares ROCm and Vulkan as backends for hosting local LLMs on AMD GPUs, concluding that the choice depends on the inference engine, GPU generation, and workload rather than being interch…
A new proposal calls for a common GPU execution and memory-management layer above CUDA, ROCm, and Intel XPU/oneAPI so that AI workloads are not tightly coupled to a single vendor, targeting 13B-class …
AMD unveiled the Threadripper Halo Station at IFA 2026 in Berlin on September 4, a desktop workstation it calls a 'personal supercomputer' that packs up to 576 GB of HBM3E memory and aims to run trill…