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 11, 00:00 UTC
main
[Feature] Batch invariant: Lora (#30097)
quanliu committed 11 months ago
Revert "[SM100] Enable fp8 compute for prefill MLA (#30746)" (#31197)
Pavani Majety committed 11 months ago
[ci] Fix Pytorch compilation test oom in 2.10 (#31194)
Angela Yi committed 11 months ago
[AMD][CI] fix v1/engine test_preprocess_error_handling (#31192)
Divakar Verma committed 11 months ago
[MoE Refactor][7/N] AITER MK (#31102)
Robert Shaw committed 11 months ago
[CI Failure] Disable mosaicml/mpt-7b and databricks/dbrx-instruct tests (#31182)
Michael Goin committed 11 months ago
[Perf] Remove blocking copy in GDN Attention (#31167)
Benjamin Chislett committed 11 months ago
[Bug] Fix `'CutlassMLAImpl' object has no attribute '_workspace_buffer'` (#31173)
Wentao Ye committed 11 months ago
[SpecDecode] Simplified alternative padded-speculation acceptance rate fix (#29845)
Lucas Wilkinson committed 11 months ago
[Doc] Add vllm-metal to hardware plugin documentation (#31174)
Michael Goin committed 11 months ago
[SM100] Enable fp8 compute for prefill MLA (#30746)
Pavani Majety committed 11 months ago
[MoE Refactor][9/N] Use modular kernel for unquantized Triton MoE (#31052)
Yongye Zhu committed 11 months ago
Gregory Shtrasberg committed 11 months ago
[UX] improve profiler error message (#31125)
Boyuan Feng committed 11 months ago
[ROCm] [Critical]: Remove unused variable (#31156)
TJian committed 11 months ago
[AMD][CI] Add "V1 Test e2e + engine" to mi325_8 Agent Pool (#31040)
Micah Williamson committed 11 months ago
[CI][Bugfix] Fix `entrypoints/openai/test_audio.py` (#31151)
Nicolò Lucchesi committed 11 months ago
[BugFix] skip language model in Encoder (#30242)
dengyunyang committed 11 months ago
Shengqi Chen committed 11 months ago
[gpt-oss] Fix harmony parser in streaming responses (#30205)
AlonKejzman committed 11 months ago