GLM-5.2 API tuning reaches 280 tokens per second before Kimi K3 launch
baseten · x · 2026-07-27
The team says it wrapped up the performance work for GLM-5.2 right before the Kimi K3 release.
An attached article claims they built the fastest API for GLM-5.2, with:
- peak throughput of 280 tokens/sec,
- average throughput around 100 tokens/sec.
The post suggests the main story is not the model itself, but the engineering needed to serve it at high speed.
Related event: Baseten Pushes GLM-5.2 to 280 tok/s(3 posts)→
More from Infra
- Engram's random reads don't suit SSDs; CPU-memory over NVLink could serve all 72 GPUs — bookwormengr · 2026-09-11
- 80% of the DIY LLM inference hype posters have already quit — it's brutally hard systems work — abhijithneil · 2026-09-11
- Hugging Face's Ultra Scale Playbook: a free book on training LLMs on GPU clusters — mdancho84 · 2026-09-11
- Is inference latency becoming the biggest bottleneck for production AI agents? — Euphoric_Sea632 · 2026-09-11
- LLM Serving Metrics Thread: Why TPOT and Uptime Make or Break User Experience — abhijithneil · 2026-09-11
- PlanetScale launches sharded Postgres: 768 servers acting as one, 1PB scale — dhruv2038 · 2026-09-11