Evidence-driven SGLang inference deployment optimization.
Like rednote-machine-learning/Inference-autopilot, 0 likes 0 Bookmark rednote-machine-learning/Inference-autopilot, 0 bookmarks 0 Optimized GPU compiler for LLM inference. Choose from a list of optimized recipes or optimize your own model via kernel fusion, autotuning, and advanced scheduling. Run benchmarks across different GPU types and configurations, track results and share experiments with the community.
Like cloudrift-ai/emmy, 0 likes 0 Bookmark cloudrift-ai/emmy, 0 bookmarks 0 Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs
Like vllm-project/guidellm, 0 likes 0 Bookmark vllm-project/guidellm, 0 bookmarks 0 Benchmark and optimize LLM inference across frameworks with ease
Like bentoml/llm-optimizer, 0 likes 0 Bookmark bentoml/llm-optimizer, 0 bookmarks 0 Evaluating frontier models on real-world ai-infra engineering tasks
Like ai-infra-bench/ai-infra-bench, 0 likes 0 Bookmark ai-infra-bench/ai-infra-bench, 0 bookmarks 0 Offline optimization of your disaggregated Dynamo graph
Like ai-dynamo/aiconfigurator, 0 likes 0 Bookmark ai-dynamo/aiconfigurator, 0 bookmarks 0 AISimulate predicts LLM serving behavior and searches for strong deployment configurations offline, without bringing up a GPU serving cluster
Like ai-dynamo/aisimulate, 0 likes 0 Bookmark ai-dynamo/aisimulate, 0 bookmarks 0 Adaptive local inference for Hermes — One model provider. Every machine. The best local configuration the hardware can safely sustain.
Like SouthpawIN/turbofit, 0 likes 0 Bookmark SouthpawIN/turbofit, 0 bookmarks 0 Reproduce Lium's LocalMaxxing leaderboard runs (7 boards, 20 Verified) on a rented Lium GPU in one script — vLLM/llama.cpp recipes, measured cost per million tokens
Like Datura-ai/lium-localmaxxing, 0 likes 0 Bookmark Datura-ai/lium-localmaxxing, 0 bookmarks 0 
