╠2️⃣│rocm
ROCm Windows · gfx1100 · BEATEK Holdings
vLLM + Step-3.7-Flash-FP8 R9700 seeking optimization
HIP
AI
Setup
Qwen3.6 on AMD GPUs: what changed since Qwen3.5 (with R9700 benchmarks)
vLLM setup with 8xR9700?
HIP
AI
Compiler
Setup
hipDeviceGetUuid still doesn't work on windows in 2026
HIP
Tools
AI
Amdgpu-dkms crashes on new Ubuntu 26.04 LTS
Running Therock on comfy
Sharing Tunable Ops results
hipEngine: ROCm-native local LLM inference for RDNA3/3.5
ComfyUI on AMD GPUs (Linux): the pitfalls that freeze your whole box
Solving the issue of dual gpu not working on Ubuntu/Cachyos
Games are slow after ROCm install
VLLM and Qwen3.6-27B-FP8 on Radeon R9700
probs offloading tensors & layers from Mac M4pro over thunderbolt 5 to usb4 rocm gpu
ROCm 7.2.2 is out — and it finally has an official RDNA 3.5 optimization guide
Severe UI Latency with Blender Built from Source on MI300X (HIP/PTX Translation bottlenecks?
HIP
Performance
Compiler
Frameworks
HIPThreads
ROCm vs Vulkan for LLM inference on AMD: what I've found across different hardware
My AMD Radeon RX 7600M XT was brought two years ago,but I want to run Rocm on my laptop.
Tools
AI
Frameworks
Setup
Qwen3.5 on AMD — what's working, what's not, and why
hipfire — from-scratch LLM inference for RDNA GPUs in Rust + HIP
HIP
AI
Performance
Tools
Qwen3.5‑2B Runs at 26 tok/s on a 2019 MacBook Pro (No ROCm, No CUDA)
Resurrecting Legacy AMD: From 2 tok/s to 37 tok/s on a 7-year-old Radeon GPU without ROCm
Stop blaming AMD silicon: Ollama / Standard Stacks vs. Custom Bare-Metal (45+ tok/s on a 2019 GPU)
3x HP Z2 Mini G1a (Ryzen AI Max+ Pro 395, 128GB) — What's the supported ROCm stack for Strix ?
[rocprofv3] torch.cuda.nvtx support and marker tracing in ROCm 6.4.4 (MI250X)
Dual gpu not happening
Difference between hipModule and hipLibrary
HIP
Does rocm aiter has fused kernels for FP4 quantization and gemm?
Show: Bypassing the 𝑂(𝑁3) Matrix Inversion Wall – 67.7x Faster in Pure PyTorch on Ryzen 9950X
Anyone running QWEN 3.5 yet? Seems there are llama issues with it?
How does Windows compare to Linux in performance right now?
Building a Custom PyTorch Backend with Rust and Vulkan on Windows
Tools
HPC
AI
HIP Threads: GPU power for teams without GPU experts
HIP
Compiler
HIPThreads
Does SCALE support the MI300X?
Compiler
Setup
Installing ROCM 7.2 on Linux Mint 22
amdrocm-core-sdk-gfx1150 apt package doesn't install rocminfo or amdsmi?
Using gplat on ROCM 7.2
BS Roformer optimisation
Rocm with lmstudio in windows
Ollama 0.15.4 with ROCm 7.2 and gfx1201
HIP
AI
GPU Reset 890m/gfx1150
AI
Frameworks
Setup
Observations on ROCm 7.1, gfx1030 and hope for the future
ROCm 7.2 vs 7.10 on 395+
ROCm on 395+ (Ubuntu 24.04)
ADTOF running really slow
[Benchmark] qingming-engine Vector Search Performance: RX 7900 XTX 24G Shows Excellent Results
** :rocket: [Benchmark] AOTriton Speed Mystery: Nightly Build vs. Staging/Dev Builds on 7900 X
Performance
Amd
Building FlashAttention with debug flags
Compiler
Omega2.0 just changed the game.