Unverified50% confidenceFactExact time
Scaleway is partnering with VSORA and ZML to contribute to a new European AI inference solution based on the Jotunn8 processor, but no specifications, timeline or performance data for Jotunn8 have been officially provided.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedMainstream inference frameworks vLLM, llama.cpp, and Ollama still support the V100 with compute capability 7.0.67% similarUnverifiedThe old model's advertised 5–11x Token Parallelism speedup has not been integrated into vLLM (confirmed in GitHub issue #12), so do not expect that speedup when deploying via vLLM.58% similarUnverifiedQAT versions of Gemma models are directly compatible with local large model tools such as Ollama and LM Studio, and can be used immediately after downloading.57% similarUnverifiedThe research team compared the diffusion-based planner DreamReasoner-8B at the 8B scale with the autoregressive planner Qwen3-8B.56% similarUnverifiedCommonly used local deployment toolchains include llama.cpp (CPU/GPU hybrid inference) and Ollama (a local server that packages quantized models).56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1063322API
curl https://kongchang.com/api/v1/knowledge/claims/1063322MCP
get_claim(id=1063322)