Speculative decoding has plenty of tricks. Which ones actually make LLMs faster? Explore 7 methods, 26 checkpoints, and a shared training and evaluation framework.
How fast ernie-research/DCore is gaining stars, and where it lands on Trendshift and GitHub Trending
Activity and trending
Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending
Oct 30 – Nov 5, 2026
Stars +24in 7 days
0510
7
Forks +0in 7 days
01
Merged PRs 0in 7 days
01
Trendshift Trendingwhere the repository ranked each day it made the top 25
Not in the Trendshift top 25 in this period
Oct 30Oct 31Nov 1Nov 2Nov 3Nov 4Nov 5
The left and right arrow keys step from day to day; Home and End go to the first and the last
Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day
Stars gained
Forks gained
Merged PRs
Fri, Oct 30, 2026
+0
+0
0
Sat, Oct 31, 2026
+2
+0
0
Sun, Nov 1, 2026
+7
+0
0
Mon, Nov 2, 2026
+5
+0
0
Tue, Nov 3, 2026
+7
+0
0
Wed, Nov 4, 2026
+2
+0
0
Thu, Nov 5, 2026
+1
+0
0
Total
+24
+0
0
1#1 on the list
7Rank that day
Not trending
Social mentions
Recent discussions about this repository across the web
1 post
1/3 More accepted tokens. Slower inference. That can happen in speculative decoding. We retrained 6 drafter recipes under shared conditions to ask: when is better acceptance worth the extra GPU time?…
llama.cpp speculative decoding measured on one RTX 3090, Qwen3.6-35B-A3B UD-Q4_K_XL, commit 3737e4137. Published figures are re-derived from the committed data by a checker that fails on drift, a coverage probe reports how many of them it actually covers, and ERRATA.md lists this study's own retracted claims.
