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 12, 04:45 UTC
main
Remove default values from `InitVar`s so that they're not stored (#29859)
Harry Mellor committed 11 months ago
Add Mistral Large 3 and Ministral 3 (#29757)
Julien Denize committed 11 months ago
[vLLM Benchmark Suite] Add default parameters section and update CPU benchmark cases (#29381)
Louie Tsai committed 11 months ago
[BugFix] add max-num-batched-token to scheduler hash (#29829)
Boyuan Feng committed 11 months ago
[CI] Fix Bad_words test for tokenizer encode/decode asymmetry (#28193)
杰兮 committed 11 months ago
[BugFix] respect VLLM_LOGGING_LEVEL in logger (#29761)
Boyuan Feng committed 11 months ago
[Core] Eliminate redundant is_encoder_decoder lookups (20-40us/step) (#29800)
Wushi Dong committed 11 months ago
Fix some Transformers nightly tests (#29802)
Harry Mellor committed 11 months ago
[CPU]Parallelize over tokens in int4 moe (#29600)
Zhang Xiangze committed 11 months ago
[CI] Renovation of nightly wheel build & generation (take 2) (#29838)
Shengqi Chen committed 11 months ago
[Chore] Move tokenizer initialization methods (#29793)
Cyrus Leung committed 11 months ago
[CI][AMD] spec_decode:eagle skip FLASH_ATTN for deepseek on ROCm (#29827)
Divakar Verma committed 11 months ago
[CI][ROCm] Fix test_correctness_sliding_window (#29243)
Divakar Verma committed 12 months ago
[BugFix] Fix index error in ngram_proposer (#29779)
usberkeley committed 12 months ago
[Misc] Update conftest for entrypoints/sagemaker test folder (#29799)
Zuyi Zhao committed 12 months ago
Add missing return in _check_vllm_model_embed_input_ids (#29834)
Johnny Yang committed 12 months ago
[Misc] Add ReplicaId to Ray metrics (#24267)
Seiji Eicher committed 12 months ago
[Misc] Throw error on unintended access to scheduler_config.max_model_len (#29771)
Wei Wei committed 12 months ago
[Core] Support reseting all running requests' KV while calling `reset_prefix_cache` (#28827)
Zhuohan Li committed 12 months ago
[responsesAPI][4] fix responseOutputItem Kimi K2 thinking bug (#29555)
Andrew Xia committed 12 months ago