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 15, 08:30 UTC
main
[Frontend][Bug Fix] Update llama4 pythonic jinja template and llama4_pythonic parser (#17917)
Kai Wu committed over 1 year ago
[V1][Spec Decode][Bugfix] Load quantize weights for EAGLE (#18290)
Ekagra Ranjan committed over 1 year ago
[Tool] Add NIXL installation script (#18172)
lkchen committed over 1 year ago
[Build/CI] Fix CUDA 11.8 build (#17679)
Tyler Michael Smith committed over 1 year ago
[Compile][Platform] Make PiecewiseBackend pluggable and extendable (#18076)
Mengqing Cao committed over 1 year ago
[Platform] Move platform check to right place (#18470)
wangxiyuan committed over 1 year ago
[Bugfix] make `test_openai_schema.py` pass (#18224)
David Xia committed over 1 year ago
[Misc] Call `ndarray.tobytes()` directly instead of `ndarray.data.tobytes()` (#18347)
Lukas Geiger committed over 1 year ago
[Misc] improve Automatic Prefix Caching example (#18554)
Reid committed over 1 year ago
[BugFix][CPU] Fix x86 SHM distributed module initialization (#18536)
Li, Jiang committed over 1 year ago
[Doc] Add stream flag for chat completion example (#18524)
Calvin Chen committed over 1 year ago
[Bugfix] Use random hidden states in dummy sampler run (#18543)
Bowen Wang committed over 1 year ago
[Doc] Support --stream arg in openai_completion_client.py script (#18388)
CYJiang committed over 1 year ago
[CI/Build] Update bamba test model location (#18544)
Harry Mellor committed over 1 year ago
[Bugfix] Add kwargs to RequestOutput __init__ to be forward compatible (#18513)
lkchen committed over 1 year ago
[Bugfix] Fix MRoPE Errors in the Qwen-VL Model When Processing Pure Text (#18526)
燃 committed over 1 year ago
Order sequence ids + config update to support specifying custom quantization layers (#18279)
aws-elaineyz committed over 1 year ago
Update default neuron config for speculation (#18274)
aws-elaineyz committed over 1 year ago
[Neuron] Update Dockerfile.neuron to use latest neuron release (2.23) (#18512)
Satyajith Chilappagari committed over 1 year ago
[Doc] Fix invalid JSON in example args (#18527)
Cyrus Leung committed over 1 year ago