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, 00:45 UTC
main
[Mypy] Better fixes for the `mypy` issues in `vllm/config` (#37902)
Harry Mellor committed 8 months ago
[CPU][UX][Perf] Enable tcmalloc by default (#37607)
Fadi Arafeh committed 8 months ago
[Model] Add AutoWeightsLoader support for jais (#38074)
grYe99 committed 8 months ago
Fix Plamo 2/3 & LFM2 for Transformers v5 (#38090)
Harry Mellor committed 8 months ago
Better weight tying check for multimodal models (#38035)
Harry Mellor committed 8 months ago
[ROCm][CI] Rename filepath test to point to correct file (#38102)
Andreas Karatzas committed 8 months ago
[Docs] Adds vllm-musa to custom_op.md (#37840)
R0CKSTAR committed 8 months ago
[Bugfix] Pass drafter quant_config to ParallelLMHead in Eagle3 (#37280)
Matthias Gehre committed 8 months ago
Fix offline mode test for Transformers v5 (#38095)
Harry Mellor committed 8 months ago
[ROCm][CI] Fix flaky Cohere/OpenAI embedding parity test (#37616)
Andreas Karatzas committed 8 months ago
[CI] Fix realtime WebSocket timeout deadlock and unhandled model validation errors (#37483)
Andreas Karatzas committed 8 months ago
[Hardware][XPU] Align memory usage with cuda on xpu (#37029)
Kunshang Ji committed 8 months ago
[ROCm][CI] Increase OpenAPI schema test timeouts (#38088)
Andreas Karatzas committed 8 months ago
[XPU] support MLA model on Intel GPU (#37143)
Kunshang Ji committed 8 months ago
[ROCm] Attention selector reordering (#36702)
Gregory Shtrasberg committed 8 months ago
[Revert] Remove CUDA torch fallbacks for fp8_mqa_logits/fp8_paged_mqa_logits_torch function (#37968)
Chauncey committed 8 months ago
[ROCm][Test] Fix ROCM_AITER_UNIFIED_ATTN attn+quant fusion test (#37640)
vllmellm committed 8 months ago
[Bugfix] Fix IndexError when accessing prev_tool_call_arr in OpenAIToolParser (#37958)
Chauncey committed 8 months ago
[Docs] Add Encoder (ViT) CUDA Graphs section to CUDA Graphs design doc (#37914)
Baorun (Lauren) Mu committed 8 months ago
[Performance] Auto-enable prefetch on NFS with RAM guard (#37673)
Artem Perevedentsev committed 8 months ago