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 12, 18:30 UTC
main
Revert "[Redo] #26368 (#28771)" (#29121)
Jialin Ouyang committed 12 months ago
[Attention] Add ROCM_AITER_MLA_SPARSE to attention backend registry (#29103)
Matthew Bonanni committed 12 months ago
[BugFix] skip combo kernel on cpu (#29129)
Boyuan Feng committed 12 months ago
[V0 Deprecation] Remove `best_of` (#29090)
Cyrus Leung committed 12 months ago
[Doc] update installation guide regarding aarch64+cuda pytorch build (#28875)
Qidong Su committed 12 months ago
[Core] Add audio_embeds support to chat completions (#29059)
jeremyteboul committed 12 months ago
[kernel][perf] support uncontiguous input for rms_norm kernel (#28103)
zhrrr committed 12 months ago
[Bugfix] Fix Plamo3 rope handling (#29092)
Cyrus Leung committed 12 months ago
[CI] Fix mypy for `vllm/v1/worker` (#29037)
Wentao Ye committed 12 months ago
[ROCm] Fix for import when building with upstream triton for gfx1100 for gpt-oss serving (#29127)
Hongxia Yang committed 12 months ago
[Bug] Fix torch warning of tf32 usage (#29112)
Wentao Ye committed 12 months ago
Xiao Li committed 12 months ago
[LoRA][2/2]Remove LoRA extra vocab (#28545)
Jee Jee Li committed 12 months ago
Wentao Ye committed 12 months ago
Update model references for OLMo3 (#29099)
Michael Goin committed 12 months ago
[CI Bugfix] Fix Kernels DeepGEMM Test (H100) (#29106)
Michael Goin committed 12 months ago
[Doc] cleanup TPU documentation and remove outdated examples (#29048)
Rob Mulla committed 12 months ago
[CI/Build] Remove skip global cleanup in test_struct_output_generate.py (#29022)
rasmith committed 12 months ago
[CI/Build] Skip lm-format-enforcer tests in test_struct_output_generate.py for now (#29021)
rasmith committed 12 months ago
Driss Guessous committed 12 months ago