DeepSeek also open-sources deepseek-recipe, replicating official API token encoding logic
deepseek_ai · x · 2026-10-20
Alongside DeepInfer, DeepSeek open-sourced deepseek-recipe (MIT), its production token encoding/decoding component aligned with the official DeepSeek API's processing logic, bringing identical API behavior to community deployments.
It is a collection of Rust libraries with Python bindings that normalizes API requests into a Conversation format, renders prompts, encodes them to token IDs with an attached tokenizer, and converts model output back into responses. The repo has 690 stars and includes Rust/Python implementations plus an encoding-decoding demo.
More from Infra
- Gufo, an open-source Strix Halo inference engine, explains its hybrid model caching design — fedeizzo · 2026-10-20
- Google Cloud network failure in Europe disrupts multiple banks including Revolut, Lloyds and HSBC — AIFlow_ML · 2026-10-20
- Arm AGI CPU benchmarks show 2x agentic workflow performance vs leading x86 chips — ryanshrout · 2026-10-20
- ISTA-DASLab's NVFP4 prefiller recovers Qwen3.8-27B low-quant accuracy with SSD streaming — magnus-m · 2026-10-20
- Google Cloud london region outage hits dozens of services; Revolut and Lloyds among affected — neal_lathia · 2026-10-20
- Splitting a ComfyUI image workflow across two Macs: model on one, text encoder on the other? — LobsterInYakuze-2113 · 2026-10-20