@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 16, 03:15 UTC

main

[Kernel][LoRA]Punica prefill kernels fusion (#11234)

Jee Jee Li committed almost 2 years ago

[Doc][3/N] Reorganize Serving section (#11766)

Cyrus Leung committed almost 2 years ago

[Bugfix][V1] Fix molmo text-only inputs (#11676)

Jee Jee Li committed almost 2 years ago

[Doc][2/N] Reorganize Models and Usage sections (#11755)

Cyrus Leung committed almost 2 years ago

[VLM] Separate out profiling-related logic (#11746)

Cyrus Leung committed almost 2 years ago

k8s-config: Update the secret to use stringData (#11679)

Suraj Deshmukh committed almost 2 years ago

[mypy] Forward pass function type hints in lora (#11740)

Lucas Tucker committed almost 2 years ago

[V1] Refactor get_executor_cls (#11754)

Rui Qiao committed almost 2 years ago

[Misc] Fix typo for valid_tool_parses (#11753)

Rui Qiao committed almost 2 years ago

[V1] Add BlockTable class (#11693)

Woosuk Kwon committed almost 2 years ago

[Bugfix] Remove block size constraint (#11723)

Cody Yu committed almost 2 years ago

[Doc] [1/N] Reorganize Getting Started section (#11645)

Cyrus Leung committed almost 2 years ago

← Newer Page 919 of 1120 Older →