How fast AmSach/maple 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
Nov 7 – Nov 22, 2026
Stars +65in 16 days
02040
31
Forks +5in 16 days
01
1
Merged PRs 0in 16 days
01
Trendshift Trendingwhere the repository ranked each day it made the top 25
Not in the Trendshift top 25 in this period
Nov 7Nov 9Nov 11Nov 13Nov 15Nov 17Nov 19Nov 21
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
Sat, Nov 7, 2026
+0
+0
0
Sun, Nov 8, 2026
+31
+1
0
Mon, Nov 9, 2026
+12
+1
0
Tue, Nov 10, 2026
+3
+1
0
Wed, Nov 11, 2026
+1
+0
0
Thu, Nov 12, 2026
+3
+0
0
Fri, Nov 13, 2026
+1
+0
0
Sat, Nov 14, 2026
+0
+0
0
Sun, Nov 15, 2026
+1
+0
0
Mon, Nov 16, 2026
+8
+1
0
Tue, Nov 17, 2026
+2
+0
0
Wed, Nov 18, 2026
+1
+1
0
Thu, Nov 19, 2026
+0
+0
0
Fri, Nov 20, 2026
+2
+0
0
Sat, Nov 21, 2026
+0
+0
0
Sun, Nov 22, 2026
+0
+0
0
Total
+65
+5
0
1#1 on the list
7Rank that day
Not trending
Social mentions
Recent discussions about this repository across the web
2 posts
JUST IN: Maple's creator says a pruned Gemma 4 26B runs at 45.4 tokens per second on a 6GB laptop GPU, versus 6.9 for the larger model. The project checks keyword matches across four tasks.
Tiny-MoE is a lightweight Mixture-of-Experts language model built entirely from scratch in native PyTorch and trained end-to-end on Kaggle using free 2× NVIDIA T4 GPUs. The project implements modern LLM techniques—including MLA, RoPE, YaRN, streaming pre-training, and efficient inference—without relying on existing model implementations.
Caching experts made model agnostic for llama. Drastically speeds up generation speed on MoE models that fully fit in the RAM but partially in Vram. WIP: Same speedup but for models that don't fit in the ram either.
Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf and PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression https://arxiv.org/abs/2405.14852