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, 23:00 UTC
main
[Model Runner V2] Fix `_compute_slot_mappings_kernel` for chunked prefill (#36580)
Nick Hill committed 8 months ago
Fix: Re-Enable EP for trtllm MoE FP8 backend (#36494)
amirkl94 committed 8 months ago
hallerite committed 8 months ago
Fix LFM2 MoE test for Transformers v5 (#36534)
Harry Mellor committed 8 months ago
Remove unused disable_fallback field (#36546)
Zhuohan Li committed 8 months ago
Wentao Ye committed 8 months ago
[BugFix] Remove incorrect assert in split_decodes_and_prefills (#36553)
Woosuk Kwon committed 8 months ago
[Model] Add HyperCLOVAX-SEED-Think-32B vision-language model support (#31471)
Hojin Yang committed 8 months ago
[Bugfix] Fix Qwen3-Next in_proj_ba weight sharding with TP > 1 (#36242)
Ajay Anubolu committed 8 months ago
[ROCm][CI] Fix ROCm GPT-OSS Eval test group (#36179)
Andreas Karatzas committed 8 months ago
[bugfix] fix nvlink for nixl/ucx (#36475)
youkaichao committed 8 months ago
[Model Runner V2] Add model_state inputs to CUDA graph capture (#36544)
Woosuk Kwon committed 8 months ago
add nemotron v3 reasoning parser (#36393)
Shaun Kotek committed 8 months ago
[MRV2] Extensible CG dispatch rework (#35959)
Lucas Wilkinson committed 8 months ago
[MTP][Misc] Clean up dead code (#36507)
Matthew Bonanni committed 8 months ago
[ROCm][CI] Prep Tests For Change To ROCM_ATTN As New Default Backend On ROCm (#36025)
Micah Williamson committed 8 months ago
[BE] Rename `should_torch_compile_mm_vit` to `should_torch_compile_mm_encoder` (#36281)
Lucas Kabela committed 8 months ago
[Model Runner V2] Use NamedTuple for `execute_model_state` (#35930)
Woosuk Kwon committed 8 months ago
[Docs] Remove the reo beacon (#36528)
Simon Mo committed 8 months ago
Taneem Ibrahim committed 8 months ago