How fast yasakani-dev/yasakani 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 12 – Nov 19, 2026
Stars +89in 8 days
0204060
54
Forks +26in 8 days
0510
8
Merged PRs 14in 8 days
0246
6
Trendshift Trendingwhere the repository ranked each day it made the top 25
Not in the Trendshift top 25 in this period
Nov 12Nov 13Nov 14Nov 15Nov 16Nov 17Nov 18Nov 19
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
Thu, Nov 12, 2026
+0
+0
0
Fri, Nov 13, 2026
+1
+8
0
Sat, Nov 14, 2026
+54
+8
2
Sun, Nov 15, 2026
+18
+6
3
Mon, Nov 16, 2026
+8
+2
6
Tue, Nov 17, 2026
+5
+2
0
Wed, Nov 18, 2026
+2
+0
3
Thu, Nov 19, 2026
+1
+0
0
Total
+89
+26
14
1#1 on the list
7Rank that day
Not trending
Social mentions
Recent discussions about this repository across the web
1 post
YASAKANI is built for Windows. I got it running on Linux (Ubuntu under WSL2) with one compiler flag. RTX 5090, Qwen3.8 27B: 1,277 tok/s on a code edit, same answer as plain llama.cpp at 76 597 tok/s…
Ollama-compatible LLM server. Beats vllm by 40% on single stream decode, and by 20% on multi stream decode, and beats ollama by much 2-4x. Made possible with custom CUDA kernels, MTP, speculation and its own 3-bit builds. Uncensors models in one command. Windows and Linux, NVIDIA. Optimized to not eat up ram.
The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, contexts up to 1M tokens, and a launcher that shows what every setting costs. Windows and Linux.
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.