GLM 5.3 Flash EXL3 on 2x DGX Spark now generates tokens 8/15% faster!
This is a AI post classified by Jev as AI infra & evals (a model release), kept by the AI Radar because it carries real work, not commentary.
GLM 5.3 Flash EXL3 on 2x DGX Spark now generates tokens 8/15% faster! PR #217 adds a fast path for the MoE decode. It was split out from rodman80 #182. We benchmarked multiple runs. Median decode speed went up 7.7% on structured output, 8.9% on code and 14.6% on JSON Update 👇
Posted by netrunner (6.8k followers) 1 days ago · 70 likes · 20.5k views · view the original post on X. Kept by the AI Radar as AI infra & evals.
More AI work like this
- Trains your own large language model from scratch using plain PyTorch. — @tom_doerr
- Here's a useful use-case for @typesafeai for a change. — @iam_zachi
- This is genius. — @daniel_mac8
- Which GPU should you use for embedding workloads? — @runpod
- Big update to the @Alibaba_Qwen Qwen3.8-Flash-Next single DGX Spark recipe! — @jvr0x
- 🔰 The Databricks Advanced Learning Festival runs September 16 through October 14, with… — @databricks
- Q: What is a trace? — @HamelHusain
- Inference scaling part 1. — @rasbt
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27.2k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:50 UTC. Full method.