Unverified50% confidenceReleaseExact time
vLLM v0.29.0新增了对Hy4-preview、Qwen3.8-Flash-Next、GraniteSWA以及NemotronH Omni Reasoning V3等模型的支持
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/15/2026
First Seen
Valid until: 12/14/2026
Sources
Related Entities
Related Claims
UnverifiedvLLM等主流推理框架已初步支持Qwen3.8-Flash-Next，但Embedding offload至CPU内存的功能仍在开发中75% similarUnverifiedQwythos-9B建立在未经审查的Qwen 3.5基础模型之上71% similarUnverifiedUnsloth新版本正式支持Qwen3.8-Flash-Next与GLM-5.3-Flash两款模型71% similarUnverified混元3支持vLLM和SGLang两种主流推理框架部署70% similarUnverified主流推理框架vLLM、llama.cpp、Ollama仍然支持计算能力7.0的V10070% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/921474API
curl https://kongchang.com/api/v1/knowledge/claims/921474MCP
get_claim(id=921474)