Repository profile
Optimized vLLM deployment for NVIDIA Blackwell (RTX 5090) on Linux Kernel 6.14. Resolves SM_120 kernel incompatibilities, P2P deadlocks, and memory fragmentation for high-performance LLM inference.
Repository updates
Get generated informatico-madrid/blackwell-linux-infra-optimizer development summaries by email, or follow the weekly and monthly RSS feeds.
Sign in to subscribe by email. RSS feeds are public.
Sign in to subscribeTracked growth, recent movement, and commit velocity from stored repository snapshots.
Latest capture 2026-07-15 03:07
5 captures since 2026-05-25
Stars from baseline +1
All tracked data
Frameworks, package managers, ecosystems, and dependency manifests found during catalog scans.
Scanned 2026-07-15 03:07
Searchable topics, generated tags, and stack labels that explain where this repository fits.
Agent instructions and tool configuration paths found in the repository tree.
Nearest indexed repositories by embedding similarity.
Achieve state of the art inference performance with modern accelerators on Kubernetes
Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.
🦖 X—LLM: Cutting Edge & Easy LLM Finetuning
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
A high-throughput and memory-efficient inference and serving engine for LLMs
Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.
