Blackwell
5 items across the graph — tagged with Blackwell.
From the graph · 5
repo
vllm-project/vllm
→repoA high-throughput and memory-efficient inference and serving engine for LLMs
sgl-project/sglang
→repoSGLang is a high-performance serving framework for large language models and multimodal models.
lightseekorg/tokenspeed
→repoTokenSpeed is a speed-of-light LLM inference engine.
AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-DFlash
→repoFully 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-ulti…
kekzl/imp
→From-scratch C++/CUDA inference engine for the NVIDIA RTX 5090 (sm_120a) — the best single-GPU backend for agentic AI: tool calling, long-context loops, reasoni…