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 14, 01:45 UTC
main
Fix MiniMax-M2 rmsnorm precision and remove useless code (#27627)
Roger Young committed about 1 year ago
[Frontend] Add `vllm bench sweep` to CLI (#27639)
Cyrus Leung committed about 1 year ago
[CI/Build] Skip cpu offloading test on AMD (#27690)
Zhewen Li committed about 1 year ago
[VLM] Add Qwen3-VL generation test (#25185)
Isotr0py committed about 1 year ago
[chore] Remove models weight on S3 logic (#27725)
Kevin H. Luu committed about 1 year ago
Feature/video support in random mm dataset (#25963)
Eugene Khvedchenya committed about 1 year ago
[Misc] Raise error for missing video metadata in `MultiModalDataParser` (#27664)
Isotr0py committed about 1 year ago
[Fix] import get_kv_cache_torch_dtype error in LMCacheConnector integration (#27670)
Yue Zhang committed about 1 year ago
[Frontend] [gpt-oss] Mcp type bug (#27689)
Alec S committed about 1 year ago
[Frontend] [gpt-oss] Tool json call parsing error retry (#27675)
Alec S committed about 1 year ago
[Bugfix] Fix modular kernel tests (#27707)
bnellnm committed about 1 year ago
[perf] Enable concurrent execution of "shared_experts" and "selected_experts" in qwen3-next (#27578)
Jiangyun Zhu committed about 1 year ago
[CI/Build] Move pre-commit only scripts to `tools/pre_commit` (#27657)
Cyrus Leung committed about 1 year ago
[Speculators] Move tests + fix integration (#27308)
Dipika Sikka committed about 1 year ago
[Bugfix] Fix non-contiguous tensor error in `rocm_unquantized_gemm_impl` (#27605)
Zhewen Li committed about 1 year ago
[CI/Build][Bugfix]Fix Quantized Models Test on AMD (#27712)
Zhewen Li committed about 1 year ago
[KV Connector] Update lmcache connector with latest compatibility (#27681)
Shaoting committed about 1 year ago
[Model] Fix Qwen3VL and Qwen3Omni after torch.compile changes (#27705)
Lukas Geiger committed about 1 year ago
[NIXL][XPU] update name of nixl wheel (#27631)
liuzhenwei committed about 1 year ago
[Build] Revert triton_kernels requirements (#27659)
Varun Sundar Rabindranath committed about 1 year ago