Is anyone here successfully running DeepSeek-V4-Flash-0731 locally with vLLM, especially on AMD MI325X? My setup: GPU: 1x AMD Instinct MI325X Model: deepseek-ai/DeepSeek-V4-Flash-0731 vLLM: 0.26.0 ROCm image --tokenizer-mode deepseek_v4 --reasoning-parser deepseek_v4 --tool-call-parser deepseek_v4 -
