v0.3.5

What's Changed

• feat(store): add thread safety analysis with clang annotations by @xiaguan in #538
• feat(master): support rpc server address parameter by @xiaguan in #530
• add notify support by @haobayuxi in #528
• [TE] revert: fix QP reclaim issues by @stmatengss in #543
• chore: bump version to 0.3.4.post1 in pyproject.toml by @ShangmingCai in #544
• [TransferEngine] Add Redis password authentication and DB selection via environment variables by @staryxchen in #512
• feat(store): add batch exist support for master by @xiaguan in #542
• [TransferEngine] Fix side effect of wild location registration by @alogfans in #552
• chore: bump version to 0.3.4.post2 in pyproject.toml by @ShangmingCai in #554
• chore: checkout specific version of yalantinglibs in script by @xiaguan in #555
• [TransferEngine]: fix compilation warning by @201341 in #550
• [TransferEngine] fix segfault when create cq failed by @doujiang24 in #535
• [Integration] feat: expose batch reg API by @stmatengss in #558
• support batch put/get api in python module by @xinranwang17 in #556
• feat(store): add zero copy batch put and get for python binding by @xiaguan in #551
• [TransferEngine] bugfix: ensure proper socket closure in destructor by @staryxchen in #566
• [TransferEngine] Add support to force MNNVL transport by MC_FORCE_MNNVL by @alogfans in #572
• [Store] Add Chaos Tests and Fix Bugs by @ykwd in #568
• Optimize slice handling to accelerate the large batch transfer operation by @SCDESPERTATE in #557
• [P2P Store] Add cuda link option when it is installed by @alogfans in #560
• [DOC] fix: Naming errors in Doc transfer-engine-python.md by @SgtPepperr in #508
• [cmake]fix cmake for centos by @qicosmos in #573
• [Doc] Add pypi install guide in the build doc by @ShangmingCai in #574
• [TransferEngine] Enable Huawei Ascend Transport for TransferEngine by @AscendTransport in #502
• [Misc] Add Issue Template in Github by @scatyf3 in #506
• [DOC] Update API description of mooncake store client by @panli889 in #548
• [DOC] Add Description for High Availability in Store by @ykwd in #576
• Disable memcpy by default and improve stress workload test by @xiaguan in #577
• [Store] Enable Client SSD Offload And Storage Persistence by @SgtPepperr in #437
• [TransferEngine] Fix retry logics in RDMA worker by @alogfans in #417
• refactor: introduce expected pattern for error handling in master service by @xiaguan in #562
• refactor(tests): enhance stress test benchmarking with zero-copy batch by @xiaguan in #586
• [TransferEngine] Enlarge default send/recv message size in etcd by @alogfans in #575
• fixed initall function by @JasonZhang517 in #591
• [DOC]: Add Description for Data Persistence and KVCache offloading in Store by @SgtPepperr in #585
• add support for asynchronous batch transfer to accelerate transfer operation by @SCDESPERTATE in #564
• [Store] Add ungister_buffer api for Store by @SgtPepperr in #596
• feat(topology): improve HCA selection by considering PCIe distance by @staryxchen in #581
• [Store] Soft Pin for Important Object by @ykwd in #587
• docs: add support for LMDeploy by @Risc-lt in #592
• [doc] Update mooncake-store doc by @LuyuZhang00 in #603
• test(client): add batch put test for duplicate keys by @xiaguan in #588
• refactor(store): remove unused value_length from PutStart functions by @xiaguan in #606
• feat(store): add ReplicateConfig support for pybindings by @xiaguan in #608
• [Store] feat: put/get tensor API for store by @stmatengss in #579
• feat(store): add get_hostname method for py bindings by @xiaguan in #617
• fix: correctly cleanup local buffer allocation by @xinranwang17 in #590
• [Doc] Update Mooncake Store Docs by @ykwd in #612
• [Mooncake Store] perf: avoid memory copy for rpc service by @qicosmos in #618
• refactor(rpc_service): separate implementation into cpp file by @xiaguan in #620
• implement genNotify interface by @haobayuxi in #600
• [DOC] Update readme by @stmatengss in #629
• [TransferEngine] Fix address already in use by @alogfans in #604
• fix(memory): Prevent integer overflow in getMemoryLocation for large memory regions by @ZeroLiu2018 in #626
• [Build] Fix nvlink allocator compile command by @ShangmingCai in #534
• ci: add --use-nvcc flag to build nvlink.so by @xiaguan in #634
• Revert "implement genNotify interface" by @ShangmingCai in #636
• [BugFix] Prevent SIGSEGV when SliceBuffer is destroyed after DistributedObjectStore::close() by @wwq2333 in #639
• [TransferEngine] Add IPv6 support [2] by @thefacetakt in #628
• [TransferEngine] Ascend Transport: add batch_transfer_sync, Debian support & bug fixes by @AscendTransport in #619
• [Store] Import Offset Allocator by @ykwd in #641
• [TransferEngine] fix the compilation warnings by @LuyuZhang00 in #643
• mooncake-common: add config class by @201341 in #582
• refactor(store): replace memory management with offset allocator by @xiaguan in #642
• [Fix] Support large global segment by @ykwd in #647
• feat(rdma): add device affinity optimization for RDMA performance by @staryxchen in #645
• [TransferEngine] Reimplement #600 posting Notify message after transfer successful by @alogfans in #635
• Remove unused files by @ykwd in #652
• docs(store): add Python API documentation for mooncake store by @xiaguan in #646
• [store] test: add mutil-threads test by @LuyuZhang00 in #611
• fix(store) : fix disk-backed replicas in size calculation and slice allocation(#653) by @SgtPepperr in #655
• refactor(store_py): convert functions to use tl::expected for error by @xiaguan in #651
• fix transfer engine: handle install transport fail by @LCAIZJ in #656
• [DOC] add SGLang RDMA trouble shooting by @stmatengss in #662
• fix(bench): use correct GPU ID in memory registration by @staryxchen in #661
• [TransferEngine] Fix NVlink accuracy drop issue by @alogfans in #663
• [Store] feat: add metadata support for tensor interface by @JasonZhang517 in #625
• [Store] Enlarge the Default KV TTL by @ykwd in #660
• [TransferEngine] Fix compile issue to make CentOS usable + Make ascend_transport timeout configurable by @AscendTransport in #658
• [Store] Master Service Support OffsetAllocater by @ykwd in #657
• [Store]feat: Add 3fs native api plugin for KVCache storage persistence by @SgtPepperr in #610
• Revert "[TransferEngine] Fix NVlink accuracy drop issue" by @ShangmingCai in #665
• feat(ci): enable CUDA support in CI workflow by @xiaguan in #637
• [TransferEngine] Add known issue about accuracy problem by @alogfans in #666
• chore: bump version to 0.3.5 in pyproject.toml by @ShangmingCai in #667
• Revert "feat(ci): enable CUDA support in CI workflow (#637)" by @xiaguan in #668

New Contributors

• @haobayuxi made their first contribution in #528
• @staryxchen made their first contribution in #512
• @SgtPepperr made their first contribution in #508
• @AscendTransport made their first contribution in #502
• @scatyf3 made their first contribution in #506
• @panli889 made their first contribution in #548
• @LuyuZhang00 made their first contribution in #603
• @ZeroLiu2018 made their first contribution in #626
• @wwq2333 made their first contribution in #639
• @thefacetakt made their first contribution in #628
• @LCAIZJ made their first contribution in #656

Full Changelog: v0.3.4...v0.3.5