Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

Websitebench
Websitebench
Omnigraph
Omnigraph
Bifrost
Bifrost
Busbar
Busbar

edurdias/capyctl-recipes

Measured CapyCTL deployment recipes per engine, model and GPU

Visit GitHub
HTML
1 contributors
Apache License 2.0
FeaturedAdvertise to 180K+ monthly visitors
Websitebench

Can AI agents reverse-engineer real websites?

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Busbar

Control what AI can do before it acts

Momentum

How fast edurdias/capyctl-recipes 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 2 – Nov 12, 2026

Stars +0 in 42 days

01

Forks +0 in 42 days

01

Merged PRs 41 in 42 days

0246
6

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

Not in the Trendshift top 25 in this period

Oct 2Oct 8Oct 14Oct 20Oct 26Nov 1Nov 7
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
DayStars gainedForks gainedMerged PRs
Fri, Oct 2, 2026+0+05
Sat, Oct 3, 2026+0+03
Sun, Oct 4, 2026+0+05
Mon, Oct 5, 2026+0+01
Tue, Oct 6, 2026+0+01
Wed, Oct 7, 2026+0+01
Thu, Oct 8, 2026+0+01
Fri, Oct 9, 2026+0+06
Sat, Oct 10, 2026+0+00
Sun, Oct 11, 2026+0+00
Mon, Oct 12, 2026+0+00
Tue, Oct 13, 2026+0+00
Wed, Oct 14, 2026+0+00
Thu, Oct 15, 2026+0+01
Fri, Oct 16, 2026+0+04
Sat, Oct 17, 2026+0+03
Sun, Oct 18, 2026+0+01
Mon, Oct 19, 2026+0+01
Tue, Oct 20, 2026+0+00
Wed, Oct 21, 2026+0+00
Thu, Oct 22, 2026+0+01
Fri, Oct 23, 2026+0+01
Sat, Oct 24, 2026+0+00
Sun, Oct 25, 2026+0+00
Mon, Oct 26, 2026+0+00
Tue, Oct 27, 2026+0+03
Wed, Oct 28, 2026+0+00
Thu, Oct 29, 2026+0+00
Fri, Oct 30, 2026+0+00
Sat, Oct 31, 2026+0+00
Sun, Nov 1, 2026+0+00
Mon, Nov 2, 2026+0+00
Tue, Nov 3, 2026+0+00
Wed, Nov 4, 2026+0+02
Thu, Nov 5, 2026+0+00
Fri, Nov 6, 2026+0+00
Sat, Nov 7, 2026+0+01
Sun, Nov 8, 2026+0+00
Mon, Nov 9, 2026+0+00
Tue, Nov 10, 2026+0+00
Wed, Nov 11, 2026+0+00
Thu, Nov 12, 2026+0+00
Total+0+041
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Nov 121 post
    • Me too: ~1,560 tok/s combined with 8 lanes, Qwen3.8-27B NVFP4 + DFlash2, on the released @vllm_project 0.32 through CapyCTL. Caveat: an RTX PRO 6000 (same chip and bandwidth as a 5090) with a 16GiB…

      Read full on X, posted by @edurdias

      @edurdias · x.com

  2. 8 days earlier
  3. Nov 42 posts
    • 6/7 I measured seven builds the same way, through CapyCTL on the same machine: NVIDIA, gittensor, QUASAR, RedHatAI, unsloth, the BF16 source and MiaAI-Lab's EXL3. Results, accuracy answers and run…

      Read full on X, posted by @edurdias

      @edurdias · x.com

    • 5/7 Accuracy holds: 98.3% on the GSM8K answers that finished in 2,048 tokens, against 98.3% for the BF16 original and 98.4% for NVIDIA's build. 30 of 30 tool calls.

      Read full on X, posted by @edurdias

      @edurdias · x.com

  4. 1 month earlier
  5. Oct 42 posts
    • Running FrogNano locally: we made a 4-bit build for TensorFold and an NVFP4 build vLLM, SGLang and TensorFold all read. On one RTX 4090 Laptop GPU via CapyCTL: 50 tok/s at 1 stream, 319 at 8, tool…

      Read full on X, posted by @edurdias

      @edurdias · x.com

    • Qwen3.8-27B NVFP4 on one GB10 through CapyCTL: TensorFold 0.6.3 / vLLM 0.30.0 / SGLang 0.5.21 tok/s, 1 stream: 42.3 / 28.7 / 31.8 8 streams: 194 / 136 / 122 Peak memory at 8: 29.5 / 50.8 / 76.6 GiB…

      Read full on X, posted by @edurdias

      @edurdias · x.com