Open Models Almanac
Methodssoftware implementationkernel & quantization library

implementation detail · filed under software implementation

FlashInfer TensorRT-LLM backend

A FlashInfer backend selected for the TensorRT-LLM MoE runner.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See kernel & quantization library for the methods filed beside it.

Also called flashinfer_trtllm.

sources
2
model
1
lab adopt it
1
strongest
used

Documented in

Evidence

2 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
optional 1used 1
↑