Top blackwell tools
Sustained, decay-weighted momentum leaders tagged “blackwell”.
- 193· newvllmA high-throughput and memory-efficient inference and serving engine for LLMsamdblackwell+1858.1
- 346· newsglangSGLang is a high-performance serving framework for large language models and multimodal models.attentionblackwell+1656.1
- 441· newtokenspeedTokenSpeed is a speed-of-light LLM inference engine.blackwelldeepseek+1054.9
- 640· newopenlakeOpenLake is a high performance storage engine for efficient LLM inference and GPU Trainingblackwellgpt+952.3
- 1226· newQwen3.6-27B-AEON-Ultimate-Uncensored-DFlashFully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/aeon-7/aeon-vllm-ultimate:latest container, tuned for long-context draft acceptance on DGX Spark. 6 HF variants (BF16/NVFP4/MTP/MTP-XS), docker-compose, and QuickStart.abliterationblackwell+1041.8
The weekly drop
Get the weekly rising list
The top risers across agents, MCP servers and dev tools, once a week in your inbox. No spam, unsubscribe anytime.