AMD MI355X hits 2,100+ tokens/sec per user on DeepSeek V4.1 Flash inference
JiaZhihao · x · 2026-10-28
Jia Zhihao announced a collaboration with AMD delivering ultra-low-latency LLM inference on Instinct MI355X GPUs: 2,100+ tokens/sec per user on DeepSeek V4.1 Flash at full model quality on 8x MI355X. AMD credited lithosAI for pushing the inference frontier with persistent megakernels on its hardware, stressing that open hardware plus instruction-level control leaves room to innovate.
Related event: Lithos AI Claims Fastest AMD Inference: 2,116 Tokens/sec Per User on MI355X(2 posts)→
More from Infra
- Statistically Lossless Qwen3.8 27B GGUF Quants Hit ~99% EAR at 23GB, Feels FP8-like — Dany0 · 2026-10-28
- Tonawanda Seneca Nation opposes data center on wetland at People's AI Assembly — AINowInstitute · 2026-10-28
- Kimi K3.1 teased to adopt DSA like DeepSeek V3.2 for better inference economics — zephyr_z9 · 2026-10-28
- VLM Run Gateway Launches: One API for Open-Weight OCR, VLM and Vision Models — spillai · 2026-10-28
- Hyperscalers issue $228B in bonds YTD, nearly 14x the 2024 total — Beth_Kindig · 2026-10-28
- Bittensor subnet Targon burns ~$2.1M of tokens from organic GPU revenue — markjeffrey · 2026-10-28