SemiAnalysis: DeepSeek's open-sourced DeepInfer lacks key inference-serving components
cHHillee · x · 2026-10-22
DeepSeek open-sourced its DeepInfer inference project days ago, but SemiAnalysis says the code is missing key components crucial for inference serving, and building them would add too many assumptions — hence DeepInfer isn't in their stack. cHHillee adds the root cause traces to InferenceX deprecating 8k/1k configurations. A notable third-party analysis of open-source inference stack maturity.
More from Infra
- GitHub moves 99.99999% of repos to Azure; per-reference quorums fix 25ms latency wall — rseroter · 2026-10-22
- Flint model weights hit HuggingFace, runs on DGX Spark, RTX GPUs and M4 Pro — testingcatalog · 2026-10-22
- ABB ships RobotStudio HyperReality on NVIDIA Omniverse; Absolute Accuracy calibration is key — lukas_m_ziegler · 2026-10-22
- Flappy Airplanes raises $1B Series A co-led by Index and Lux for new GPU primitives — gabriel1 · 2026-10-22
- Researcher: the final megakernel isn't a kernel but a transformer in an endless loop — DimitrisPapail · 2026-10-22
- SPCX earnings call highlights 'computer per watt' metric as AI value shifts down the stack — mobileraj · 2026-10-22