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, 05:30 UTC
main
[Platform][Kernel] platform-specific kernel loading (#25823)
Hank_ committed about 1 year ago
[Bugfix][Hardware][RISC-V] Limit supported dtypes to float32 to avoid scheduler segfault (#26228)
ihb2032 committed about 1 year ago
[Bugfix] Always apply MM processor even when no MM items are passed (#26240)
Cyrus Leung committed about 1 year ago
[Bugfix]: Assertion error when using FlashInfer backend (#25933)
Simon Danielsson committed about 1 year ago
[Perf][Easy] Early stop in request_block_hasher (#26112)
Jialin Ouyang committed about 1 year ago
Add documentation for granite 4 tool calling (#26175)
Maximilien de Bayser committed about 1 year ago
[Bugfix] Allow `--skip-tokenizer-init` with `echo and return_token_ids` (#26238)
Cyrus Leung committed about 1 year ago
[Easy] Add str repr for IterationStats (#26232)
22quinn committed about 1 year ago
[Model] Use `merge_by_field_config` for MM models (H-L) (#26230)
Cyrus Leung committed about 1 year ago
[Renderer] Clean up renderer code (#26216)
Cyrus Leung committed about 1 year ago
[Frontend] Cache chat template kwargs resolution (#26227)
Isotr0py committed about 1 year ago
[CPU] Refine batch reorder of CPU attention backend (#26096)
Li, Jiang committed about 1 year ago
[V1] [Hybrid] Remove code to override default CUDA graph configuration (#26226)
Thomas Parnell committed about 1 year ago
Fix tensor device and dtype placement in Qwen2VL model (#26219)
yuafng committed about 1 year ago
[Model] CLIP Embedding Support (#26010)
Cyrus Leung committed about 1 year ago
[Bugfix] Fix `_reqs_to_process` leak on abort (#26012)
Nicolò Lucchesi committed about 1 year ago
[Core] Enable decode of context length equal to max model length (#26168)
Yannick Schnider committed about 1 year ago
Add Olmo 3 reasoning parser (#26054)
Luca Soldaini committed about 1 year ago
Revert "Add batch invariant kernel override for FlashInfer backend [2/n]" (#26220)
Cyrus Leung committed about 1 year ago
[CI Failure] fix_test_auto_prefix_cache_support (#26053)
Huamin Li committed about 1 year ago