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 4, 13:45 UTC
main
[Bugfix] Fix broken example opeanai client (#41088)
Isotr0py committed 6 months ago
[Attention][Spec Decode] Allow independent drafter attention backend selection (#39930)
Matthew Bonanni committed 6 months ago
[Frontend]Responses API supports Tool/Function calling with streaming with required (#40700)
Chauncey committed 6 months ago
[Bugfix] Remove tokenizer encode/decode calls from Olmo3 reasoning parser (#40855)
yzong-rh committed 6 months ago
[Test] Fix test_dynamic_shapes_compilation for torch 2.12 (#40743)
Angela Yi committed 6 months ago
[Model][DSV4] Support base model (#41006)
Jee Jee Li committed 6 months ago
[xpu] bump up vllm-xpu-kernel v0.1.7 (#41019)
Kunshang Ji committed 6 months ago
[Model Runner V2] Skip attention metadata rebuild before draft prefill (#40410)
Giancarlo Delfin committed 6 months ago
[ROCm][CI] Add missing quantization methods and fix online quant test failures (#39801)
Andreas Karatzas committed 6 months ago
[Perf] Update TRTLLM supported MoE routing methods (#39141)
Wei Zhao committed 6 months ago
[Docker] Install numactl CLI in CUDA runtime image (#41032)
Zhewen Li committed 6 months ago
[Bugfix] use `served_model_name` for multimodal error message (#41003)
Moritz Sanft committed 6 months ago
Deprecate support for Transformers v4 (#40389)
Harry Mellor committed 6 months ago
[Model] Add MiMo-V2.5 support (#40967)
Isotr0py committed 6 months ago
[Bugfix] Fix k_norm weight sharding in MiniMaxM2Attention when total_num_kv_heads < tp_size (#38191)
Xiaoshuang Wang committed 6 months ago
Add system_fingerprint field to OpenAI-compatible API responses (#40537)
Simon Mo committed 6 months ago
[Examples] Resettle generate examples. (#36464)
wang.yuqi committed 6 months ago
[Bugfix] Install libcublas-dev in Dockerfile for FlashInfer CuTe DSL JIT (#39855)
Roy Wang committed 6 months ago
[DSV4] Add silu clamp limit to shared expert (#40950)
Yongye Zhu committed 6 months ago
[Bugfix] Remove invalid deepstack boundary check for Qwen3-VL (#40932)
Isotr0py committed 6 months ago