scaleapi/llm-engine Issues
Integrate TensorRT-LLM
Closedself host on runnpod
Updated 1Control frequency - completion
Updated 3Test out spot instances
UpdatedSpeculative decoding
UpdatedRetNet adaptation
UpdatedInvestigate CUDA graphs
Updated[Feature Request] support InternLM
Updated 1Model ids =/= Fine Tune Id?
Closed 1Add github sidebar
Closed 1Llama-2-70B support
Closed 7[Tracking] Allow wandb tracking
Closed 1Import completion error
Closed 2GKE Helm deployment
Closed 3Preparing dataset for LLaMa-13b-chat
Updated 2Comparison benchmarks?
Updated 1