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 13, 13:15 UTC
main
Restore PlaMo2 unit test as `pfnet/plamo-2-1b` now supports `transformers >=4.56` (#28019)
Shinichi Hemmi committed about 1 year ago
[V0 deprecation] Remove no longer used `get_metadata_cls` (#28370)
Lucas Wilkinson committed about 1 year ago
Xiake Sun committed about 1 year ago
[CI] lora/test_mixtral.py : Add additional expected outputs due to flakiness (#28322)
Varun Sundar Rabindranath committed about 1 year ago
[ROCm][Platform] Add RX7900XTX device id in _ROCM_DEVICE_ID_NAME_MAP (#28279)
JartX committed about 1 year ago
[Kernel] Fix fused_gdn_gating (#28343)
Jiangyun Zhu committed about 1 year ago
[CI/Build] Temporary fix to LM Eval Small Models (#28324)
Zhewen Li committed about 1 year ago
Fix cu_num_generated_tokens slicing logic in LogprobsLists.slice() method (#28214)
usberkeley committed about 1 year ago
[Core] Separate out attention metadata building logic from prepare inputs (#26764)
Lucas Wilkinson committed about 1 year ago
[Core] Simplify async KV output aggregation (#28327)
Nick Hill committed about 1 year ago
[CI] Fix flaky `test_eagle_correctness` test (#28364)
Nicolò Lucchesi committed about 1 year ago
[Misc] Add some comments in qwen3-next (#28267)
Jiangyun Zhu committed about 1 year ago
[ROCm] Add env to enable/disable aiter triton gemm (#28321)
Yong Hoon Shin committed about 1 year ago
[Misc] fix typo and add detailed log (#28178)
Ning Xie committed about 1 year ago
fix: close issue 28338 by fixed python version (#28339)
yihong committed about 1 year ago
[chore] Move some wikimedia images to S3 (#28351)
Kevin H. Luu committed about 1 year ago
[Performance][gpt-oss] Revert gpt-oss max cudagraph size to 1024 (#28345)
Mohammad Miadh Angkad committed about 1 year ago
[Bugfix] Fix test fused quant layernorm tests (#27865)
ElizaWszola committed about 1 year ago
Remove setuptools upper bound constraint (<80) (#28337)
Cole Murray committed about 1 year ago
[Feat] Drop-in Torch CUDA Profiler (#27841)
Benjamin Chislett committed about 1 year ago