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 6, 17:00 UTC
main
[Bugfix] fix Qwen3.5 tool calling bug (#36774)
Chauncey committed 8 months ago
[Model Runner V2] Fix processed logits in sample() (#37144)
Woosuk Kwon committed 8 months ago
[Kernel] Add FlashInfer MoE A2A Kernel (#36022)
leo-cf-tian committed 8 months ago
[Model] Add HyperCLOVAX-SEED-Think-14B language model support (#37107)
bigshanedogg committed 8 months ago
[Bugfix] Avoid LD_PRELOAD check on MacOS (#37145)
Li, Jiang committed 8 months ago
Andreas Karatzas committed 8 months ago
[ROCm][CI] Fix engine teardown and text normalization to stabilize voxtral test (#37138)
Andreas Karatzas committed 8 months ago
[XPU] Add deepseek_scaling_rope fused kernel (#36612)
Wang, Yiting committed 8 months ago
rasmith committed 8 months ago
[responsesAPI][ez] add a unit test for SimpleContext logprobs (#37126)
Andrew Xia committed 8 months ago
In-Tree AMD Zen CPU Backend via zentorch [1/N] (#35970)
Lalithnarayan C committed 8 months ago
[GDN] add a config for gdn kernel selection (#36647)
Jiangyun Zhu committed 8 months ago
[Feature] Add Azure Blob Storage support for RunAI Model Streamer (#34614)
Hari committed 8 months ago
[Misc] Add online audio_in_video test (#36775)
Isotr0py committed 8 months ago
[Frontend] Remove `torchcodec` from audio dependency (#37061)
Isotr0py committed 8 months ago
[Build] Upgrade xgrammar to get a security fix (#36168)
Russell Bryant committed 8 months ago
[Frontend] Reduce chat template warmup logging levels (#37062)
Nick Hill committed 8 months ago
[Bugfix] Fix xgrammar dtype mismatch on macOS CPU inference (#32384)
Karan Bansal committed 8 months ago
[Feature] Add InstantTensor weight loader (#36139)
arlo committed 8 months ago
[Frontend] Avoid startup error log for models without chat template (#37040)
Cyrus Leung committed 8 months ago