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 5, 23:30 UTC
main
[ROCm][CI] Fix flaky GPTQ compile correctness test (#38161)
Andreas Karatzas committed 7 months ago
[ROCm][CI] Fix wvSplitKrc mock argument order in test_rocm_unquantized_gemm (#38167)
Andreas Karatzas committed 7 months ago
[Refactor] Remove unused utils (#38153)
Wentao Ye committed 7 months ago
DOC: Documentation pages fixes (#38125)
Mateusz Sokół committed 7 months ago
[XPU] Disable xpu graph by default (#38193)
Kunshang Ji committed 7 months ago
[Doc] Fix outdated reference to CUDAGraphManager (#38209)
Cyrus Leung committed 7 months ago
[Model] Use helper function to run MM processors with token inputs (where applicable) (#38018)
Cyrus Leung committed 7 months ago
[Bugfix] Fix DeepGemm E8M0 accuracy degradation for Qwen3.5 FP8 on Blackwell (#38083)
Vadim Gimpelson committed 7 months ago
[cpu][ci] remove soft-fail for Arm CI and add quant model tests (#37691)
Fadi Arafeh committed 7 months ago
[Model] Add torch.compile support for InternVL vision encoder (#38049)
Terry Gao committed 7 months ago
[Bugfix] Fix benchmark_fused_collective.py (#38082)
Jee Jee Li committed 7 months ago
Add `/v1/chat/completions/batch` endpoint for batched chat completions (#38011)
Matej Rojec committed 7 months ago
[Bugfix][CI] Fix Marlin FP8 Linear Kernel for Compressed Tensors Format (#38092)
BadrBasowid committed 7 months ago
Relocate Encoder CUDA graph manager (#38116)
Woosuk Kwon committed 7 months ago
[Tool Parser][1/3] Pass tools to ToolParser constructor (#38029)
Flora Feng committed 7 months ago
[Revert] Remove DeepGEMM availability check in DeepseekV32IndexerMetadataBuilder (#38076)
Chauncey committed 7 months ago
[Misc] Optimized check to encapsulate both CUDA and ROCm platforms (#34549)
Andreas Karatzas committed 7 months ago
Disable dual stream execution of input projection for Qwen3 (#38152)
Xin Yang committed 7 months ago
Fix minimax m2.5 nvfp4 kv scales weight loading (#37214)
Wei Zhao committed 7 months ago
[Bugfix] Fix Qwen3.5-FP8 Weight Loading Error on TPU (#37348)
Jacob Platin committed 7 months ago