Unverified50% confidenceCautionExact time
The deployment method officially recommended by vLLM does not support running FP8 models on Turing architecture cards such as the 2080 Ti.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/19/2026
First Seen
Valid until: 11/17/2026
Sources
魔改2080Ti本地部署Qwen3 27B实测：FP8量化低成本方案
Related Claims
UnverifiedV100所属的Volta架构不具备原生FP8硬件加速支持，FP8原生支持于Hopper架构的H10071% similarUnverifiedvLLM only supports Linux environments and requires GPU resources; CPU execution requires the processor to support specific instruction sets.67% similarUnverifiedSGLang currently cannot run the Qwen3 27B NVFP4 MTP-XS model, whereas vLLM already supports it.67% similarUnverifiedThe A100's Ampere architecture supports the TF32 format, while the V100's Volta architecture does not.62% similarUnverifiedStarting with PyTorch 2.0, the ROCm backend was incorporated into official first-tier support, and vLLM completed its adaptation for AMD GPUs in 2024.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/775273API
curl https://kongchang.com/api/v1/knowledge/claims/775273MCP
get_claim(id=775273)