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, 21:45 UTC
main
[openapi] refactor render related openapi [3/N] (#36749)
Ning Xie committed 8 months ago
[Bugfix] Fix Qwen3-VL timestamp mismatch when using num_frames without fps (#36136)
Weiguang Li committed 8 months ago
Disable cascade attention by default (#36318)
Michael Goin committed 8 months ago
[compile] aot_compile should respect VLLM_DISABLE_COMPILE_CACHE (#36358)
Richard Zou committed 8 months ago
fix(lora): use replaced_module_name in pooling model name check (#36402)
Ethan T. committed 8 months ago
platforms: Fix Ray DP startup crash (#36665)
Itay Alroy committed 8 months ago
[ci] Update rtol for test_classification (#36556)
Angela Yi committed 8 months ago
Add: Eagle3 support for Qwen3.5 (#36658)
Rahul Tuli committed 8 months ago
[Refactor] Remove Molmo2 processor wrapper (#36667)
Cyrus Leung committed 8 months ago
fix(minicpmv): fix audio inference by handling meta device in init_re… (#36751)
tc-mb committed 8 months ago
[Bugfix] Support other quantization methods in glm41v (#36321)
LoganJane committed 8 months ago
[NemotronH] Small fix reasoning parser (#36635)
roikoren755 committed 8 months ago
[XPU]Bug fix for some unexpected error when use AgRs backend on XPU device. (#36593)
YiSheng5 committed 8 months ago
Remove unused config field from Gemma2 (#36672)
Harry Mellor committed 8 months ago
[UX] Infer dtype for local checkpoint (#36218)
Isotr0py committed 8 months ago
[NIXL][1/N] Refactor `kernel_block_size` detection (#35752)
Nicolò Lucchesi committed 8 months ago
JartX committed 8 months ago
AITER MLA backend: Avoid CPU sync in _build_decode (#35765)
pschlan-amd committed 8 months ago
[Refactor] Remove deadcode in Responses API serving (#36726)
Flora Feng committed 8 months ago
[Hardware][NIXL] set default kv buffer type for different platform (#36438)
liuzhenwei committed 8 months ago