21:00
2026-10-01
gist.github.com
ai-infrastructure
2x CMP 170HX for LLM inference: unlock, cross-root P2P, serving (vLLM, EPYC/ROMED8-2T)
A developer documented running two unlocked NVIDIA CMP 170HX mining cards (GA100, A100-class) for LLM inference on a single AMD EPYC 7443 / ASRock Rack ROMED8-2T host, unlocking them to 64 GB and 74 Sā¦