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
[Misc] Add removed encoder-decoder models to previously supported models list (#24961)
Isotr0py committed about 1 year ago
[Bugfix] Fix unable to run encoder model when disable_hybrid_kv_cache_manager is true (#24571)
lianyibo committed about 1 year ago
[Core/DBO][1/N] Add Dual-Batch Overlap mechanism to VLLM (#23693)
Sage Moore committed about 1 year ago
[Core][MultiModalHasher] Don't convert memoryviews to bytes during hashing (#24925)
Lukas Geiger committed about 1 year ago
[Model] Clean up and simplify Mamba2 Metadata Usage in both V0 and V1 (#24331)
Chih-Chieh Yang committed about 1 year ago
[CI] Add Decode Context Parallelism (DCP) test to CI (#24487)
Ming Yang committed about 1 year ago
(doc): set cmake c++ compatible standard when building on MacOS CPU. (#23483)
TeeKen Lau committed about 1 year ago
feat: Add Grafana and Perces monitoring dashboards for vLLM (#23498)
liangwen12year committed about 1 year ago
[Docs] move benchmarks README to contributing guides (#24820)
Ye (Charlotte) Qi committed about 1 year ago
Move `SpeculativeConfig` from `config/__init__.py` to `config/speculative.py` (#24904)
Harry Mellor committed about 1 year ago
[Feat][EPLB] A novel static EPLB placement strategy for MoE models. (#23745)
Chen Bruce committed about 1 year ago
[Mamba] Support TP>1 with quantization for mamba2 mixer in case `n_groups % tp_size == 0` (#24593)
tomeras91 committed about 1 year ago
[Bugfix] remove duplicate tokens streamed in required tool choice streaming (#23312)
Cheng Kuan Yong Jason committed about 1 year ago
[benchmark] Add triton version in the moe tuned config (#24769)
Jee Jee Li committed about 1 year ago
[QWEN NEXT] Fused MoE kernels Optimization configs (#24924)
Saman A. Pour committed about 1 year ago
[Bug] [Spec Dec]: Fix kv_cache dtype mismatch for Eagle3 drafter on FP8 target (#24505)
vllmellm committed about 1 year ago
[Bugfix] Fix sequence parallelism bug when enable pipeline parallelism (#24021)
cascade committed about 1 year ago
Remove V0 Encoder-Decoder Support (#24907)
Woosuk Kwon committed about 1 year ago
[XPU] Fix circular import error. (#24927)
Kunshang Ji committed about 1 year ago
Upgrade flashinfer to 0.3.1 (#24470)
Lu Fang committed about 1 year ago