AMD's vLLM-ATOM Plugin Supercharges DeepSeek-R1, Kimi-K2, and gpt-oss-120B AI LLM Inference on Instinct MI350 and MI400 Accelerators
…Mature optimizations upstreamed for all: ATOM serves as a temporary proving ground for new optimizations; once stabilized, kernels, optimization strategies, and new features are upstreamed to vLLM’s native ROCm backend, benefiting…