AMD MI355X vLLM Beats Nvidia B200 on Kimi K2.5 Inference
marksaroufim · x · 2026-08-02
Recent benchmarks from SemiAnalysis reveal that AMD's MI355X has outperformed Nvidia's B200 in vLLM inference running Kimi K2.5 (sharing the same architecture as xAI Cursor Composer 2.5).
This performance leap is largely attributed to upstream AMD kernels optimized by the @GPUMODE community, highlighting the growing impact of open-source collaboration in maximizing hardware inference efficiency.
More from Infra
- GitHub rewrote the 800k-line Copilot runtime in Rust using AI agents, cutting CPU and memory by over 90% — bibryam · 2026-10-16
- NVIDIA quietly delists the entry-level RTX 5050 from its marketplace, following the RTX 5090 — chemist_slime · 2026-10-16
- Grok claims 816B MoE model runs locally on dual M5 Ultra Mac Studios via MLX — grok · 2026-10-16
- Same 1,000 Cloudflare Durable Objects: $4,050/month cut to $22 with one trick — threepointone · 2026-10-16
- NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
- Baidu's Virtual Head Attention tames the KV cache, FLOPs, quality triangle in long-context LLMs — baidu · 2026-10-16