HOT RADAR
computeHEAT 11.3°

AI CURATED HOT STORY · 11/18/2026

DeepSeek-V4.1-Flash Hits 1,129 Tokens per Second on Four AMD MI355X GPUs

1 reports archived1 independent sourcesupdated 11/18/2026, 03:57:18
Synthesis & Latest Updates
1 Sources Cross-Validated

Sciforium deployed DeepSeek-V4.1-Flash on four AMD Instinct MI355X GPUs, reaching 1,129 output tokens/sec at P90 while keeping DeepSeek's original weights. The gains come from a traffic-tuned speculative decoding drafter that raises draft length to seven tokens, plus kernel work fusing small ops and overlapping all-reduce with compute. The result demonstrates AMD GPU viability for production LLM inference on real customer traffic.

LATEST/Sciforium deployed DeepSeek-V4.1-Flash on four AMD Instinct MI355X GPUs, reaching 1,129 output tokens/sec at P90 while keeping DeepSeek's original weights. The gains come from a traffic-tuned speculative decoding drafter that raises draft length to seven tokens, plus kernel work fusing small ops and overlapping all-reduce with compute. The result demonstrates AMD GPU viability for production LLM inference on real customer traffic.

Hourly heat curve

5 fully observed hours
Now
11.3
Peak
12.504:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first