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
vllm-project/llm-compressor avatar

vllm-project/llm-compressor

GitHub

State-of-the-art LLM compression, built for production inference with vLLM

Python3,960 stars731 forksApache-2.0
compressionquantization

Momentum

vllm-project/llm-compressor has 3,960 GitHub stars. It gained +8 stars over 3 recorded days in the last 7 days and +24 over 6 recorded days in the last 30 days (snapshots through Nov 10, 2026).

Its biggest recent day was Oct 21, 2026, with +9 stars.

It currently ranks #2867 daily, #2651 weekly, #3049 monthly by momentum on Trending Repos; its best-ever rank is #362.

Trending Repos first recorded it on May 16, 2026.

Rankings

PeriodRankScore
Daily
#28671.7
Weekly
#26512.3
Monthly
#30492.3
How scoring works

Engagement

Total stars
Daily new stars

Similar trending repositories

  • headroomlabs-ai/headroomCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.Python79,336 stars#368 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
  • mw00/project-mayaRun GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.C++2,780 stars#580 this week
  • lz4/lz4Extremely Fast Compression algorithmC12,757 stars#592 this week
  • SYSTRAN/faster-whisperFaster Whisper transcription with CTranslate2Python26,659 stars#739 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.Python2,666 stars#1018 this week

Embeds

Best rank #362
vllm-project/llm-compressor badge
Markdown
Recent daily star gains
DateStars gainedTotal starsForks gained
Nov 6, 2026+33,949+3
Nov 5, 2026+23,946+1
Nov 4, 2026+33,944+3
Oct 28, 2026+53,9230
Oct 22, 2026+23,897+4
Oct 21, 2026+93,895+3