DeepSeek Uses More Tokens but is Faster per Single Request
Sentdex · x · 2026-07-03
Sentdex observed that DeepSeek consumes about 2.5x more tokens than GLM 5.2 IQ4 but is 5x faster at batch size=1. Once concurrency is introduced, vLLM's concurrent processing capabilities take off rapidly. He also noticed a performance drop in vLLM tensor parallelism at batch size=2 before it recovers, and asked the community for insights on this behavior.
More from Infra
- RTK Terminal Compression Cuts Tokens but Leaves Your AI Coding Bill Unchanged — Bartaseth · 2026-09-11
- SF Compute founder: buying compute is 'an absolutely awful experience' right now — IgorCarron · 2026-09-11
- SmolVM open-sources persistent computer infrastructure for agents that outlive chat sessions — aniketmaurya · 2026-09-11
- PyTorch Day Korea 2026 launches first offline conf, CFP closes Sept 13 — PyTorch · 2026-09-11
- Local LLM server dilemma: 4x CMP-170HX (price up 53% in 20 days) vs Mac Studio M5 Ultra — rumboll · 2026-09-11
- llama.cpp lands Flash Attention tuning for RDNA4, big prefill gains on AMD — pmttyji · 2026-09-11