yabs.io

Yet Another Bookmarks Service

Search

Results

[https://github.com/ollama/ollama/issues/2637] - - public:mzimmerm
amd, apu, gfx900, install, pytorch, rocm - 6 | id:1491350 -

Latest (0.1.27) docker image with ROCm works for me on Ryzen 5600G with 8GB VRAM allocation. Prompt processing is 2x faster than with CPU. Generation runs at max speed even if CPU is busy running other processes. I am on Fedora 39. Container setup: HSA_OVERRIDE_GFX_VERSION=9.0.0

[https://www.videocardbenchmark.net/compare/4086vs3548vs4405vs4989vs3930/GeForce-GTX-1060-(Mobile)-vs-GeForce-GTX-1060-vs-Ryzen-7-5700G-with-Radeon-Graphics-vs-Radeon-Ryzen-5-5600GT-vs-Ryzen-5-2500U-with-Radeon-Vega] - - public:mzimmerm
amd, apu, compare, gpu, passmark - 5 | id:1490036 -

Compare Distinct graphics cards with AMD APUs. Result: Buy Ryzen 5700G, or AMD Ryzen 5 5600GT as GPU is the same. BUT Ryzen 5700G has 25% better CPU

[https://www.techpowerup.com/gpu-specs/?mfgr=AMD&architecture=GCN%205.0&sort=generation] - - public:mzimmerm
amd, apu, database, gcngpu, gfx902, good, gpu - 7 | id:1490009 -

Database of AMD GPUs. Here we can see that 2500U is Vega 8 mobile , which is GCN 5.0. This is only supported in ROCm up to 4.5.2!!

[https://stackoverflow.com/questions/77708142/how-can-i-fetch-vram-and-gpu-cache-size-in-linux] - - public:mzimmerm
amd, apu, command, linux, memory - 5 | id:1489838 -

If you have AMD GPU as I do then you can grab PCI ID for the device with lspci command executed with -D flag (shows PCI doamin) and read the following file cat /sys/bus/pci/devices/${pci_slot}/mem_info_vram_total, it contains GPU VRAM size in bytes.

[https://medium.com/@rafaelmanzanom/ditching-cuda-for-amd-rocm-for-more-accessible-llm-inference-ryzen-apus-edition-92c3649f8f7d] - - public:mzimmerm
ai, amd, apu, compile, gfx902, install, pytorch, rocm - 8 | id:1489810 -

Train LLM on AMD APU. In this scenario, we’ll use an APU because most laptops with a Ryzen CPU include an iGPU; specifically, this post should work with iGPUs based on the “GCN 5.0” architecture, or “Vega” for friends. We’ll use an AMD Ryzen 2200G in this post, an entry-level processor equipped with 4C/4T and an integrated GPU.

Follow Tags


Export:

JSONXMLRSS