EschaLabs
/

escha-runtime-qwen3dense

Model card Files Files and versions

escha-runtime-qwen3dense / README.md

Commit History

Clarify that 64k context and 8-9 streams are not simultaneous

36bb7bf
verified

yzhwang commited on about 13 hours ago

escha 1.2.0: docs + changelog for tensor parallelism

e05fa1a
verified

yzhwang commited on about 19 hours ago

escha 1.1.1: docs + changelog for the cuda:0 device fix

ca22b2f
verified

yzhwang commited on about 20 hours ago

Escha Runtime qwen3dense — escha 1.1.0+qwen3dense SGLang wheel, serve.sh, cookbook

bc55caa

yzhwang commited on 1 day ago