Unverified50% confidenceFactExact time
The deployment container for FP4-Local is ghcr.io/local-inference-lab/vllm, and the tags in the model card are inconsistent between release-10152026 and release-10142026.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/18/2026
First Seen
Valid until: 11/1/2026
Sources
Related Entities
Related Claims
UnverifiedvLLM released the v0.30.1rc0 pre-release version, introducing dense NVFP4 kernel and MoRI kernel image support for AMD MI355 accelerator cards (PR #58281).69% similarUnverifiedNVFP4 quantization is not 4-bit for the whole model: the vision encoder, connector, Mamba convolutions, and embedding stay in BF16, and the MoE router stays in FP32.68% similarUnverifiedFPS (Feature Pack Stack) is a feature delivery unit in the SAP S/4HANA version system, sitting between major versions and Support Packages; some AI components were previously available only for the latest FPS.66% similarUnverifiedOne change in v0.32.0rc2 is to pin the evaluation of DeepSeek-V4.1-Flash-NVFP4 to its FP8-Engram version.66% similarUnverifiedThe Qwen3.8-27B model is available in multiple formats including Safetensors, GGUF, NVFP4, NVFP4 GGUF variants, and GPTQ-Int4 quantized versions.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1064237API
curl https://kongchang.com/api/v1/knowledge/claims/1064237MCP
get_claim(id=1064237)