vLLM Claims Decode Performance Within 6% of DeepInfer Using Wide-EP and EPLB

1 reports 1 reporting sources 1 hours agoNew

Understand the event

AI overview

vLLM said its Wide-EP and EPLB configuration can achieve decode performance within 6% of DeepInfer on the AgentX workload at 200 P90 TPS. Under those same workload and performance conditions, vLLM said it can generate $39 per GPU per hour in revenue using DeepSeek’s off-peak pricing.

Generated by AI from reports · Updated 1 hours ago

Latest development10/21 08:31 (UTC+8)

vLLM reports decode performance within 6% of DeepInfer on AgentX vLLM · X

Report timeline

Follow the reports to explore different sides of the event.

10/21

08:31
vLLM · X
vLLM reports decode performance within 6% of DeepInfer on AgentX
vLLM says Wide-EP and EPLB let it match DeepInfer’s decode performance within 6% and generate $39/gpu/hr in revenue at DeepSeek’s off-peak pricing, at 200 P90 TPS on the AgentX workload. The post links to further details at https://t.co/l0ZVo31hft.

The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue

Event heat trend

There is not enough continuous observation data to plot a trend yet.

Keep reading

Latest daily · Issue 28Mistral AI releases Voxtral 3 speech models and a voice agent SDK