GitHub / bigai-nlco / TokenSwift
From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigai-nlco%2FTokenSwift
Stars: 85
Forks: 9
Open issues: 0
License: mit
Language: Python
Size: 61.6 MB
Dependencies parsed at: Pending
Created at: 2 months ago
Updated at: 18 days ago
Pushed at: about 1 month ago
Last synced at: 16 days ago
Topics: deepseek, inference, llm-inference, llm-serving, llms, qwen, speculative-decoding, transformer
Loading...