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, 16:15 UTC
main
[docs] Improve wide-EP performance + benchmarking documentation (#27933)
Seiji Eicher committed 11 months ago
[Docs] Update EPLB docs (#30426)
Michael Goin committed 11 months ago
[LMCache] Fix breakage due to new LMCache version (#30216)
Nick Hill committed 11 months ago
[bug] Fix "Current vLLM config is not set." warnings when FlashInfer attention is used (#30241)
Po-Han Huang (NVIDIA) committed 11 months ago
Jialin Ouyang committed 11 months ago
{Deprecation] Remove tokenizer setter (#30400)
Cyrus Leung committed 11 months ago
[P/D] KV Load Failure Recovery/Abort Configuration (#26813)
Will Eaton committed 11 months ago
[Bugfix] Fix HunyuanOCR cross-image contamination in batch processing (#30344)
Anker committed 11 months ago
[Chore] Delay recent deprecations (#30398)
Cyrus Leung committed 11 months ago
[Misc] Consistent case for `vllm bench serve` results (#30403)
Matthew Bonanni committed 11 months ago
[Docs] Generate full list of metrics in user docs (#30388)
Mark McLoughlin committed 11 months ago
Lucas Wilkinson committed 11 months ago
[Core] Whisper enable `FULL_DECODE_ONLY` CudaGraph (#30072)
Nicolò Lucchesi committed 11 months ago
[BugFix] Fix minimax m2 model rotary_dim (#30384)
Roger Young committed 11 months ago
[CPU] Support for Whisper (#30062)
Aditya Tewari committed 11 months ago
[Bugfix] tpu_model_runner: set vllm config context when calling reset_dynamo_cache() (#30331)
Daniele committed 11 months ago
[Bugfix] Fix the issue where DeepSeek v3.2 cannot use structured_output (#30371)
Chauncey committed 11 months ago
[cpu][ci] Add CPU Attention Tests for Neon Backend (#30347)
Fadi Arafeh committed 11 months ago
[ROCm][CI] Attempt to fix the failures under a subgroup of the e2e the test group (#29358)
Andreas Karatzas committed 11 months ago
[CMake][Build]: Remove unused ACL CMake env variables (#30339)
Radu Salavat committed 11 months ago