§ tools · storyline

Transformers: Patch release v5.8.1

Hugging Face Transformers releases patch v5.8.1, fixing DeepSeek V4 integration issues including CSA mask collapse and a WeightConverter regex bug misidentifying shared experts.

May 13 · 05:21:23 · primary fetch1 sourceupdated May 13 · 05:21:23

Patch release v5.8.1 This release is mainly to fix the Deepseek V4 integration!!! [fix] Add fatal_error to ContinuousBatchingManager so the serving... by @qgallouedec, @remi-or Fix WeightConverter regex incorrectly matching shared_experts as experts by @silencelamb, @claude Fix deepseek v4 by @ArthurZucker (#45892) Deepseek v4 csa mask collapse by @ArthurZucker, @Sawyer117 (#45928)

read full article on github.com ↗

§ sources1 publication · timeline below

github.comTransformers: Patch release v5.8.1primary05:21:23