https://github.com/llmsresearch/specstream
Fast LLM inference with 2.8x speedup using speculative decoding
https://github.com/llmsresearch/specstream
inference largelanguagemodel llms speculative-decoding
Last synced: 27 days ago
JSON representation
Fast LLM inference with 2.8x speedup using speculative decoding
- Host: GitHub
- URL: https://github.com/llmsresearch/specstream
- Owner: llmsresearch
- License: mit
- Created: 2025-07-24T01:50:10.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2025-07-24T02:18:05.000Z (7 months ago)
- Last Synced: 2025-09-29T16:36:06.189Z (4 months ago)
- Topics: inference, largelanguagemodel, llms, speculative-decoding
- Language: Python
- Homepage: https://pypi.org/project/specstream/
- Size: 39.1 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0