blackwell

A high-throughput and memory-efficient inference and serving engine for LLMs

SGLang is a high-performance serving framework for large language models and multimodal models.

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

OpenLake is a high performance storage engine for efficient LLM inference and GPU Training

TokenSpeed is a speed-of-light LLM inference engine.

Fully 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.

GLM-5.2-NVFP4-REAP-469B serving on SM120 (4× RTX PRO 6000 Blackwell) — one-command vLLM launch recipe, 250K context, DeepSeek Sparse Attention + MTP speculative decode

Practical local LLM recipes and benchmarks for RTX 5060 Ti setups

One-command vLLM installation for NVIDIA DGX Spark with Blackwell GB10 GPUs (sm_121 architecture)

DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding

GLM-5.2 (744B/40B MoE) on a 4× DGX Spark / GB10 (sm_121) cluster: portable Triton sparse-MLA kernels, a data-free expert prune, MTP draft, and a one-script bootstrap.

From-scratch C++23/CUDA inference engine for the NVIDIA RTX 5090 (sm_120a). The best single-GPU backend for agentic AI: tool calling, long-context loops, reasoning and concurrent sub-agents. Decode beats llama.cpp b9976 by 42-48% on dense GGUF (measured 2026-07-12), at-or-ahead of vLLM on NVFP4. 100% written by Claude Code.

NVFP4 inference on Blackwell GeForce (RTX 5090/5080/5070 Ti/RTX PRO 6000) — SM120 patches for vLLM + FlashInfer + CUTLASS. 175 tok/s on Qwen3.6-35B MoE.

LLM fine-tuning with LoRA + NVFP4/MXFP8 on NVIDIA DGX Spark (Blackwell GB10)

Reproducible recipe: serve abliterated Gemma-4-12B (gemma4_unified) at 50-118 tok/s on no-NVLink Blackwell (SM120) via vLLM nightly + ModelOpt FP8/NVFP4 + MTP spec-decode.

Multi-model LLM serving for NVIDIA DGX Spark with vLLM, web UI, and tool calling

Out-of-tree vLLM plugin and open format spec for NVFP4-CB / FP8-CB product-codebook weights — 2-6 bit-per-weight LLM quantization served on native Blackwell tensor cores.

7.67× LoRA / 8.35× Full FT speedup for Qwen3.5 (0.8B–27B) on NVIDIA DGX Spark — wall-clock parity with rented H100. Lossless within BF16. Three-command interactive wizard handles model picker, data validator, training, and merge.

Lna-Lab production pipeline: GGUF -> modelopt-format NVFP4 + working MTP head for vLLM on RTX PRO 6000 Blackwell (SM120). Stages 2 (NVFP4) and 3 (MTP graft) are Lna-Lab originals; stage 1 (GGUF->bf16) reuses li-yifei/gguf-to-nvfp4.