Unverified50% confidenceFactExact time
vLLM v0.27.0 adds support for the K-EXAONE-2.0-750B-A37B large-scale MoE model.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedDeepSeek-R1-Distill-Qwen-32B is based on Qwen-2.5-32B and was derived by distilling knowledge from the full 671B MoE architecture model.65% similarUnverifiedTypical representatives of the MoE architecture include Mixtral 8x7B and DeepSeek-V2.65% similarUnverifiedvLLM v0.27.0 provides complete full-stack support for the Kimi K3 model, with all related components landing at once in the same version.63% similarUnverifiedMeta's LLaMA 3 series has a maximum scale of 405B, and DeepSeek-V3 is approximately 671B (mixture-of-experts architecture).63% similarUnverifiedRecently popular models such as DeepSeek-V2/V3 and Qwen2-MoE all adopt the MoE architecture.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/898650API
curl https://kongchang.com/api/v1/knowledge/claims/898650MCP
get_claim(id=898650)