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 8, 12:30 UTC
main
[WideEP] Fix nvfp4 DeepEP High Throughput All2All backend (#33738)
Tyler Michael Smith committed 9 months ago
[torch.compile] Stop doing unnecessary FakeTensorProp in PiecewiseCompileInterpreter (#34093)
Richard Zou committed 9 months ago
[Redo] Add `--trust-remote-code` to dataset bench args (#34251)
Cyrus Leung committed 9 months ago
[Bugfix] Fix Worker.load_model context-manager composition for sleep mode (#34021)
tianshu-Michael-yu committed 9 months ago
[Misc] Add run one batch script that supports profiling (#32968)
Lucas Wilkinson committed 9 months ago
[ROCm][CI] Fix test_sequence_parallel.py location in AMD CI pipeline (#34280)
Micah Williamson committed 9 months ago
bnellnm committed 9 months ago
[CI] Add pip caching to cleanup_pr_body workflow (#32979)
7. Sun committed 9 months ago
[Misc] Add pre-commit hook to catch boolean ops in with-statements (#34271)
Tyler Michael Smith committed 9 months ago
[torch.compile] Disable recursive pre_grad_passes (#34092)
Richard Zou committed 9 months ago
[Misc][Spec Decode] support different load config for draft model (#34022)
Zhengkai Zhang committed 9 months ago
[BugFix] Fix async EPLB hang with DeepEP LL all2all backend (#32860)
Ilya Markov committed 9 months ago
[Perf] Move eplb rebalance algo to async thread (#30888)
Ilya Markov committed 9 months ago
[Feature] Warn about unrecognized environment variables (#33581)
Gregory Shtrasberg committed 9 months ago
[SM100] Resubmit FMHA FP8 prefill for MLA (#31195)
Pavani Majety committed 9 months ago
[Bugfix] Fix mamba cache dtype for Qwen3.5 (#34200)
Roger Wang committed 9 months ago
[Benchmarks] Fix attention benchmark smoke test (#34269)
Matthew Bonanni committed 9 months ago
[Bugfix] Fix weights offloading for sleep mode (#32947)
J Seppänen committed 9 months ago
Convert online APIs to use Renderer (#34084)
Reagan Lee committed 9 months ago
[Misc] Introduce ec_both role EC (encoder cache) connector (#34182)
Qi Wang committed 9 months ago