| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
[Chores] Offset Allocator Test Fix & Docs Fix (#806) * Fix unit test * fix docs | 10 个月前 | |
add ascend direct transport to mooncake store (#835) Co-authored-by: youxiao <youxiao@huawei.com> | 9 个月前 | |
[TransferEngine] Update to support CANN 8.2.RC1 (#714) | 10 个月前 | |
revert: rollback v0.3.7-dev to 39bbe9c This commit reverts upstream/v0.3.7-dev back to 39bbe9cc10663f437f8b3a4487013e80f08ee2ba. | 5 个月前 | |
[Misc] Mooncake EP & Mooncake Backend (#805) * Initialize a mooncake backend * Add pybind * Fix incorrect backend registration * Fix wheel building of mooncake_ep * Add a fake allreduce implementation * Introduce transfer_engine to mooncake_backend * Add a basic CPU proxy execution framework * Implement a seemingly working allgather * Remove mooncake_ep's dependency on etcd * Implement _allgather_base * Implement allreduce * Implement alltoall * Use an even-odd pattern for data transfer * Add a set_host_ip method * Switch to an extended-API implementation of the Mooncake backend * Implement broadcast * Implement barrier * Extend Mooncake backend to CPU * Support more operations for reduction * Fix the backend-worker coordination logic * Optimize CPU worker with a callback pattern * Add a timeout-based broken-ranks detection * Merge EP module into Mooncake's build system * Share transfer buffer across all worker instances * Switch to a more robust approach to detect broken ranks * Specify CUDA device for test_mooncake_backend.py * Explicitly stop mooncake worker * Use transfer engine's notifications to implement collective signals * Remove the unused all_reduce_without API * Switch to mooncake backend for test_mooncake_ep.py * Support both IB and RoCE * Fix EP unit test * Pass the auto-detected nic_id to EP Buffer * Fix CMake conditional branches when PYTORCH_CMAKE_PATH is not set * Fix ibgda syncing for RoCE * Revert "Share transfer buffer across all worker instances" This reverts commit 964e0a96 * Implement _reduce_scatter_base * Make CPU backends aware of broken ranks * Fix .typos.toml * Add a perf test for mooncake backend * Support more dtypes for reduction * Revert "Use transfer engine's notifications to implement collective signals" This reverts commit f20ffb21 * Share worker thread among all process groups * Share transfer engine among all process groups * Fix unit tests * Add a warmup phase for transfer engine * Fix transfer engine buffer locations * Fix incorrect calculation of mooncake ep buffer * Do not use timeout detection in mooncake_ep tests * Update mooncake backend perf test * Demangle per-group buffer offset from the shared taskId * Stop allocating the useless cuda_counter_buffer and cuda_data_buffer * Split the task list into a CPU region and a CUDA region * Add a warmup for test_mooncake_backend_perf.py * Switch from raw cudaEvent to torch::Event * Fix MooncakeWorkCuda::wait() to make it compatible with cuda graphs * Add doc * Fix perf test * Implement all-gather for perf test * Move impl of MooncakeEpBuffer's member functions to .cpp * Change gathered_experts to broken_nodes to make the API more consistent * broken_nodes should be broken_ranks * API rename * Fix format * Enable WITH_EP option in CI * Try installing torch in advance in CI * Set TORCH_CUDA_ARCH_LIST in CMakeLists.txt * Install required dependencies in the CI CUDA environment * [CI] Add the matching PyTorch * [CI] Add a workaround for missing CUDA::nvToolsExt * Remove unused pybind base class declaration of MooncakeBackendOptions * Support set_device_filter * Remove unused headers for ep_py.cpp * Build the EP-wheel with setuptools on CI * [CI] Add the build-with-ep process to release.yaml * Minor format fix * Update build guide * Fix docs * Only build EP wheel with torch==2.8.0 * Add a torch version assertion for Mooncake Backend * Fix some python typing * Use the correct group for EP's initial data sharing * API: invert broken_ranks and change into active_ranks * Followup fix for inverting the API * Fix format * Bug-fix in mooncake_ep_kernel.cu * Mooncake EP has to be built with USE_CUDA on * Fixed some issues according to the review * Fix bug | 9 个月前 | |
[Docs] Update Obsolete Content & Fix Minor Problems (#880) * Fix bugs * Update get and put description * Update allocator description * Address review comments * Update strong consistency description * Update error code | 9 个月前 | |
agg for heterogeneous_rdma_transport (#859) Co-authored-by: AscendTransport <ascendtransport@yeah.net> | 9 个月前 | |
[DOC] docs: add lmcache integration documentation (#336) * docs: add lmcache integration documentation * docs: add LMCache integration documentation and update README | 1 年前 | |
[DOC] Update lmcacheV1-deployment.md (#438) | 1 年前 | |
docs: add support for LMDeploy (#592) * docs: add support for LMDeploy * chore: rm specific ip address in doc | 11 个月前 | |
revert: rollback v0.3.7-dev to 39bbe9c This commit reverts upstream/v0.3.7-dev back to 39bbe9cc10663f437f8b3a4487013e80f08ee2ba. | 5 个月前 | |
[TransferEngine] change: auto discover topology & install transport. (#73) * [TransferEngine] change: auto discover topology & install transport. Signed-off-by: doujiang24 <doujiang24@gmail.com> | 1 年前 | |
[Doc] Add sglang benchmark results (#266) | 1 年前 | |
[Doc] SGLang HiCache Intergration (#833) | 9 个月前 | |
add instructions for running on AMD GPU (#689) Co-authored-by: Li <haoli1@amd.com> | 11 个月前 | |
[TransferEngine] Add guide in testing Transfer Engine, and remove confusing output in transfer engine (#754) * [TransferEngine] Add guide in testing Transfer Engine, and remove confusing output in transfer engine. * Removing extra words | 10 个月前 | |
fix Naming errors in doc transfer-engine-python.md (#508) | 1 年前 | |
revert: rollback v0.3.7-dev to 39bbe9c This commit reverts upstream/v0.3.7-dev back to 39bbe9cc10663f437f8b3a4487013e80f08ee2ba. | 5 个月前 | |
docs: add troubleshooting steps for QP allocation error (#707) Added documentation for handling "Failed to create QP: Cannot allocate memory" error in troubleshooting.md, including solution options. Signed-off-by: staryxchen <staryxchen@tencent.com> | 11 个月前 | |
[Docs] Update Obsolete Content & Fix Minor Problems (#880) * Fix bugs * Update get and put description * Update allocator description * Address review comments * Update strong consistency description * Update error code | 9 个月前 | |
[Docs] Update Obsolete Content & Fix Minor Problems (#880) * Fix bugs * Update get and put description * Update allocator description * Address review comments * Update strong consistency description * Update error code | 9 个月前 | |
[Build] Deprecate stale adaptor usage to reduce whl package size (#529) Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com> | 1 年前 | |
[Build] Deprecate stale adaptor usage to reduce whl package size (#529) Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com> | 1 年前 |
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 10 个月前 | ||
| 9 个月前 | ||
| 10 个月前 | ||
| 5 个月前 | ||
| 9 个月前 | ||
| 9 个月前 | ||
| 9 个月前 | ||
| 1 年前 | ||
| 1 年前 | ||
| 11 个月前 | ||
| 5 个月前 | ||
| 1 年前 | ||
| 1 年前 | ||
| 9 个月前 | ||
| 11 个月前 | ||
| 10 个月前 | ||
| 1 年前 | ||
| 5 个月前 | ||
| 11 个月前 | ||
| 9 个月前 | ||
| 9 个月前 | ||
| 1 年前 | ||
| 1 年前 |