DeepSeek open-sources DeepInfer, its production inference engine
DeepSeek claims 155 trillion tokens a day and 96% cache hits; KV cache and load balancing are not fully released.
62
Product
DeepInfer
- Mentions · 7d6
- Mentions · 30d6
- All mentions6
- First seenOct 20, 2026
- Last mentioned4d ago
Timeline
6 articles · newest firstUS orders federal civilian agencies to purge DeepSeek within 60 days
The ban covers Hangzhou DeepSeek technology and third-party tools built on it, with written CISA exemptions possible.
78
DeepSeek open-sources DeepInfer inference engine under Apache 2.0
DeepInfer serves V4.1-Flash on top of vLLM, and deepseek-recipe mirrors official API token processing for self-hosting.
52
China and DHS move on open models as DeepSeek ships V4.1 Flash
The commerce proposal is not law, and DeepSeek also published DeepInfer, the inference stack it uses to serve tokens.
52
DeepSeek open-sources DeepInfer, inference stack for V4.1-Flash
The feed contained only the headline; license, hardware targets, and release notes were not in the text.
48
DeepSeek open-sources its DeepInfer inference engine
The Hacker News item only links to deepseek-ai/DeepInfer and gives no release notes.
46
Appears with
- DeepSeekvendor · 4
- DeepSeek-V4.1-Flashai model · 2
- Department of Homeland Securityorganization · 2
- vLLMproduct · 1
- Xiaomivendor · 1
- deepseek-recipeproduct · 1
- Cybersecurity and Infrastructure Security Agencyorganization · 1
- Anthropicorganization · 1
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4ai model · 1
- NVIDIAvendor · 1
- DeepSeek-V4.1-Flash-1017ai model · 1
- DeepSeekorganization · 1
- DeepSeekproduct · 1
- Hangzhou DeepSeek Artificial Intelligence Co.vendor · 1
- Reflectionvendor · 1
- V4.1-Flashai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.