Python
ZinYY/OnlineSPEC
[ICML 2026] When Drafts Evolve: Speculative Decoding Meets Online Learning
★ 127
Stars
20 forks · 2 open issues
flat
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
12.7
Momentum / 100
see the breakdown below
8mo ago
Created
last push 3mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | flat, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 6.6 | last push 3mo ago; decays to zero at 180 days |
| Scale | 15 | 6.1 | 127 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 12.7 | sum of the above |
Detail
| Topics | efficient-inferencelarge-language-modelsllmon-policy-distillationonline-learningparallel-decodingspeculative-decoding |
| Matched on | LLM & Inference (large-language-models) |
| Short window | +0 stars over 7 days = 0.0/day |
| Long window | +1 stars over 26 days = 0.0/day |
| Lifetime average | 0.54 stars/day over 237 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |