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, 17:30 UTC
main
[MoE] Move remaining PrepareAndFinalize to prepare finalize folder (#39009)
Jackmin801 committed 6 months ago
[Docs]Add documentation for bench serve visualization arguments (#40539)
Sophie du Couédic committed 6 months ago
[Spec Decode] Move `SpecDecodeBaseProposer` out of `eagle.py` (#40732)
Matthew Bonanni committed 6 months ago
[Bugfix] Fix DeepSeek V2-Lite Accuracy drop (#40673)
bnellnm committed 6 months ago
[Bugfix] Fix workspace resize leaking reserved GPU memory (#39226)
czhu-cohere committed 6 months ago
[NVIDIA] Add sm_110 (Jetson Thor) to CUDA 13.0 build targets (#39233)
Johnny committed 6 months ago
[MoE] Move xpu moe to fused_moe/experts/ (#40568)
Jackmin801 committed 6 months ago
[DP][Ray] Pin DP control bundle to same node as first GPU bundle (#39167)
shaharmor98 committed 7 months ago
[kv_offload+HMA][10/N]: Support load with multiple KV groups (#39402)
Or Ozeri committed 7 months ago
bnellnm committed 7 months ago
[CI] Split disaggregated tests into own test-area (#40623)
Nicolò Lucchesi committed 7 months ago
[ROCm] Implement GPU-to-NUMA-node detection (#40015)
pschlan-amd committed 7 months ago
[XPU] Upgrade torch 2.11 for xpu (#37947)
Kunshang Ji committed 7 months ago
[Bugfix] Make Attention Backend Auto-Selection Batch-Invariance-Aware (#40193)
Srreyansh Sethi committed 7 months ago
[Model] Support Hy3 preview (#40681)
stevenkuang committed 7 months ago
[Bugfix] Include inductor and functorch configs in compilation cache key (#40627)
Richard Zou committed 7 months ago
[Misc] use model arch converter for bidi models identification (#40701)
Isotr0py committed 7 months ago
[XPU][CI]Temporary disable 3 cases on Intel GPU in CI (#40683)
xiangdong committed 7 months ago
[CPU] Added faster exp routine for lower precision data types. (#38112)
almayne committed 7 months ago
[Compilation] Refactor SiluMul activation+quant Fusion Pass (#39684)
BadrBasowid committed 7 months ago