How fast MiaAI-Lab/DeepSeek-V4.1-Flash-1017-4x-DGX-Sparks-TensorFold 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 28 – Nov 13, 2026
Stars +22in 17 days
0123
3
Forks +16in 17 days
0123
3
Merged PRs 12in 17 days
0510
8
Trendshift Trendingwhere the repository ranked each day it made the top 25
Not in the Trendshift top 25 in this period
Oct 28Oct 31Nov 3Nov 6Nov 9Nov 12
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
Wed, Oct 28, 2026
+0
+3
8
Thu, Oct 29, 2026
+0
+2
0
Fri, Oct 30, 2026
+0
+3
0
Sat, Oct 31, 2026
+1
+0
0
Sun, Nov 1, 2026
+0
+1
0
Mon, Nov 2, 2026
+3
+0
1
Tue, Nov 3, 2026
+1
+0
0
Wed, Nov 4, 2026
+1
+0
3
Thu, Nov 5, 2026
+2
+2
0
Fri, Nov 6, 2026
+1
+3
0
Sat, Nov 7, 2026
+3
+1
0
Sun, Nov 8, 2026
+1
+0
0
Mon, Nov 9, 2026
+2
+0
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
+0
+0
0
Total
+22
+16
12
1#1 on the list
7Rank that day
Not trending
Social mentions
Recent discussions about this repository across the web
1 post
Lots of important improvements and fixes to DeepSeek V4.1 Flash 1017 for 4x DGX Sparks 🔥 - Tool calls are much more reliable - No more memory blowup on long chats - Weights load 3x faster (!) -…
DeepSeek-V4.1-Flash on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8-1.9x code, 2.5x multi-stream, 1.7-1.95x prefill vs the vLLM kit, exact speculative decoding. Work in progress.
