Swival/ds4-m5

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 15 – Oct 26, 2026

Stars +2 in 42 days

Forks +0 in 42 days

Merged PRs 0 in 42 days

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 15Sep 21Sep 27Oct 3Oct 9Oct 15Oct 21

Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day	Stars gained	Forks gained
Tue, Sep 15, 2026	+1	+0
Wed, Sep 16, 2026	+0	+0
Thu, Sep 17, 2026	+0	+0
Fri, Sep 18, 2026	+0	+0
Sat, Sep 19, 2026	+0	+0
Sun, Sep 20, 2026	+0	+0
Mon, Sep 21, 2026	+0	+0
Tue, Sep 22, 2026	+0	+0
Wed, Sep 23, 2026	+0	+0
Thu, Sep 24, 2026	+0	+0
Fri, Sep 25, 2026	+1	+0
Sat, Sep 26, 2026	+0	+0
Sun, Sep 27, 2026	+0	+0
Mon, Sep 28, 2026	+0	+0
Tue, Sep 29, 2026	+0	+0
Wed, Sep 30, 2026	+0	+0
Thu, Oct 1, 2026	+0	+0
Fri, Oct 2, 2026	+0	+0
Sat, Oct 3, 2026	+0	+0
Sun, Oct 4, 2026	+0	+0
Mon, Oct 5, 2026	+0	+0
Tue, Oct 6, 2026	+0	+0
Wed, Oct 7, 2026	+0	+0
Thu, Oct 8, 2026	+0	+0
Fri, Oct 9, 2026	+0	+0
Sat, Oct 10, 2026	+0	+0
Sun, Oct 11, 2026	+0	+0
Mon, Oct 12, 2026	+0	+0
Tue, Oct 13, 2026	+0	+0
Wed, Oct 14, 2026	+0	+0
Thu, Oct 15, 2026	+0	+0
Fri, Oct 16, 2026	+0	+0
Sat, Oct 17, 2026	+0	+0
Sun, Oct 18, 2026	+0	+0
Mon, Oct 19, 2026	+0	+0
Tue, Oct 20, 2026	+0	+0
Wed, Oct 21, 2026	+0	+0
Thu, Oct 22, 2026	+0	+0
Fri, Oct 23, 2026	+0	+0
Sat, Oct 24, 2026	+0	+0
Sun, Oct 25, 2026	+0	+0
Mon, Oct 26, 2026	+0	+0
Total	+2	+0

#1 on the list
Rank that day
Not trending

ivanfioravanti/ds4-metal

DeepSeek 4 Flash local inference engine for Metal

9310

antirez/ds4

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

24.1k2.4k

Entrpi/ds4

CUDA Blackwell performance fork of antirez/ds4 (DeepSeek-V4-Flash): ~4x prefill, ~1.5x decode, continuous batching, weight server, DSpark

7617

Anemll/ds4-ssd

DeepSeek V4 Flash specific inference engine. SSD MoE expert paging (slot-bank) + disk KV cache for long agent sessions. Metal-first, narrow & high-performance.

336

Fringe210/llama.cpp-deepseek-v4-flash-cuda

C++

Experimental implementation of DeepSeek v4 flaash in llama.cpp

244

lxe/dsx

Rust

DeepSeek-V4.1-Flash-1017 (552B MoE) on 2x RTX 3090 + 128 GB RAM: Rust + CUDA engine and 2-bit quant. 30-37 tok/s decode.

7013

alesha-pro/llama.cpp

C++

LLM inference in C/C++

5610

atbender/deepseek-v41-flash-mac-mini

Python

Run original DeepSeek V4.1 Flash FP4/FP8 weights on a 16 GB M1 Mac mini with bounded SSD streaming in MLX. Recipe, benchmarks, and demo.

895

Entrpi/ds4-on-spark

Shell

Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark, and full continuous batch support

41132

Momentum