VendorDeep
Home Intelligence Vendors Insights 🔥Decision-Radar About
中文 EN
Login Register
🌏 检测到您的语言为中文,是否切换到中文版? 去中文版
Home Intelligence Vendors Insights 🔥Decision-Radar About
中文 English
Login Register

Reports

AI-generated structured vendor updates

Filter

×
Active Filters Clear All
Keyword: MoE ×
22 Total Reports
2/2 Page
Research Other 1970-01-01

Z.ai GLM-5.2 Open-Source: 744B MoE, 1M Context, MIT License as Geopolitical Shield

Z.ai releases GLM-5.2: 744B MoE with 40B activated parameters, 1M input and 131K output context, under MIT license. Released one day after Anthropic Fable 5's government takedown, it offers a downloadable, unbanable alternative with Anthropic API compatibility for zero-code migration, giving enterprises a sovereign AI option.

View Details Impact: Major
NVIDIA Other 1970-01-01

SGLang 0.5.13: Two-Stage MoE Routing Prefetch & Sparse KV Cache Deliver 25x Inference Speedup

SGLang 0.5.13 introduces MoE-specific two-stage routing prefetch (lightweight proxy network to preload top-k expert weights) and sparse KV cache (grouped by activation path), achieving 25x inference speedup on NVIDIA GB300 NVL72. On A100, throughput +65%, latency -40%, memory -10%, routing overhead -62%, outperforming vLLM.

View Details Impact: Major
Previous
1
Next

© 2024 VendorDeep AI. All rights reserved.

Support: vendordeep@vendordeep.com Sitemap Privacy Policy Terms of Service