Trending Repos
TrendingRisersNewestTopicsCollectionsCompare
TrendingRisersNewestTopicsCollectionsCompare
Trending Repos

Trending Repos tracks GitHub momentum from stars, forks, and rank history.

Explore

TrendingRisersNewestTopicsCollections

Tools

SearchCompareBadgesSubmit a repo

Project

AboutStatsDevelopersContactPrivacy
Back to trending
jaredpalmer/kev avatar

jaredpalmer/kev

GitHub

Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own

Python9,942 stars679 forksApache-2.0
decision-modeljevqwen3

Momentum

jaredpalmer/kev has 9,942 GitHub stars. It gained +133 stars in the last 7 days and +993 in the last 30 days (snapshots through Nov 11, 2026).

Its biggest recent day was Oct 14, 2026, with +73 stars.

It currently ranks #992 daily, #1026 weekly, #877 monthly by momentum on Trending Repos; its best-ever rank is #163.

Trending Repos first recorded it on Sep 27, 2026.

Rankings

PeriodRankScore
Daily
#99211.9
Weekly
#102611.9
Monthly
#87715.6
How scoring works

Engagement

Total stars
Daily new stars

Similar trending repositories

  • NandhaKishorM/layaNon-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.Python35,381 stars#442 this week
  • modelscope/ms-swiftUse PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).Python16,084 stars#1885 this week
  • vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMsPython96,712 stars#361 this week
  • synchopate/llama-modchip🐋 Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs). SwiGLU-H2, Stockfish-PVS L3 & 13ms Claude Code restore.Python918 stars#397 this week
  • Asymptote-Labs/agent-beaconThe cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBuGo3,398 stars#635 this week
  • syv-ai/HyperQwenServe large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.

Embeds

Best rank #163
jaredpalmer/kev badge
Markdown
Recent daily star gains
DateStars gainedTotal starsForks gained
Nov 11, 2026+169,933+2
Nov 10, 2026+229,917+1
Nov 9, 2026+169,895+1
Nov 8, 2026+159,879+1
Nov 7, 2026+229,864+1
Nov 6, 2026+209,842+1
Nov 5, 2026+229,822+2
Nov 4, 2026+299,800+1
Nov 3, 2026+199,7710
Nov 2, 2026+169,7520
Nov 1, 2026+159,736+2
Oct 31, 2026+279,721+1
Oct 30, 2026+329,694-2
Oct 29, 2026+419,662+4
Python
2,666 stars
#1018 this week