[Misc] Minimum requirements for SageMaker compatibility#11575

Closed

nathan-az wants to merge 12 commits intovllm-project:mainfrom nathan-az:main

+2,345-923

Commits on Dec 28, 2024

Implement sagemaker required endpoints /invocations, /ping, and alternate docker build

Nathan Azrak
authored and
nathan-az
committed
Update deploying_with_k8s.md with AMD ROCm GPU example (#11465 )

authored and
nathan-az
committed
[Bugfix] Fix TeleChat2ForCausalLM weights mapper (#11546 )

jeejeelee
authored and
nathan-az
committed
[Misc] Abstract the logic for reading and writing media content (#11527 )

DarkLight1337
authored and
nathan-az
committed
[Doc] Add xgrammar in doc (#11549 )

ccjincong
authored and
nathan-az
committed
[VLM] Support caching in merged multi-modal processor (#11396 )

DarkLight1337
authored and
nathan-az
committed
[MODEL] LoRA support for Jamba model (#11209 )

ErezSC42
authored and
nathan-az
committed
[Misc]Add BNB quantization for MolmoForCausalLM (#11551 )

jeejeelee
authored and
nathan-az
committed
[Misc] Improve BNB loader to handle mixture of sharded and merged weights with same suffix (#11566 )

Isotr0py
authored and
nathan-az
committed
[Bugfix] Fix for ROCM compressed tensor support (#11561 )

selalipop
authored and
nathan-az
committed
[Doc] Update mllama example based on official doc (#11567 )

heheda12345
authored and
nathan-az
committed
Change /ping to post endpoint per AWS documentation

Nathan Azrak
authored and
nathan-az
committed