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 7, 22:45 UTC
main
[CI] Fix ColBERT HF comparison tests on AMD CI + refactor (#34567)
Andreas Karatzas committed 9 months ago
[feat] Add per-block extra_keys to KV events (#33304)
zhongdaor-nv committed 9 months ago
Andreas Karatzas committed 9 months ago
Kata Coder committed 9 months ago
[Realtime] Add Qwen3-ASR realtime streaming support (#34613)
pougetat committed 9 months ago
[Kernel] Optimize sample_recovered_tokens_kernel (#34974)
Xin Yang committed 9 months ago
Support prompt_embeds for pooling requests in output processor (#34904)
Li committed 9 months ago
[Misc] Fix mypy errors in vllm/profiler and remove from exclude list (#34959)
Taneem Ibrahim committed 9 months ago
Rohan Potdar committed 9 months ago
[Kernel] [Helion] [9/N] Canonicalize GPU variant names to base model names (#34928)
Yanan Cao committed 9 months ago
[CI/Build] Add opentelemetry libs in default vllm build (requirements/common.txt) (#34466)
Vlad Tiberiu Mihailescu committed 9 months ago
[LoRA] Support Quantized Adapters (#30286)
yugong333 committed 9 months ago
Lucas Wilkinson committed 9 months ago
Bump Flashinfer Version and Re-enable DeepSeek NVFP4 AR+Norm Fusion (#34899)
Wei Zhao committed 9 months ago
[AMD][CI] Fix test_custom_allreduce for A100 testgroup (#34735)
Ryan Rock committed 9 months ago
[CI] Revert PRs 34818 and 33600 (#34979)
Lucas Wilkinson committed 9 months ago
[Test] Add FP8 KV Cache Testing for MLA Backends (#34473)
Wei Zhao committed 9 months ago
[CI] Remove failing prime-rl integration test (#34843)
Michael Goin committed 9 months ago
[compile] Fix torch.compile time discrepancy in logging. (#34912)
Zhengxu Chen committed 9 months ago
[compile] Move torch_aot_compile directory under torch_compile_cache (#34831)
Zhengxu Chen committed 9 months ago