Skip to content

GitLab

"git@developer.sourcefind.cn:change/sglang.git" did not exist on "c23eda8589f62eb9dc94ae44c6bccf976125351d"
Switch branch/tag
  1. 23 Nov, 2023 1 commit
  3. 22 Nov, 2023 1 commit
  5. 14 Aug, 2023 1 commit
  7. 10 Aug, 2023 1 commit
  9. 19 Jul, 2023 1 commit
  11. 14 Jul, 2023 2 commits
  13. 13 Jul, 2023 1 commit
  15. 17 May, 2023 1 commit
  17. 23 Mar, 2023 1 commit
  19. 08 Mar, 2023 1 commit
  21. 12 Jan, 2023 1 commit
  23. 09 Dec, 2022 1 commit
  25. 06 Dec, 2022 1 commit
    • Chang Liu's avatar
      Add support for next cusparse release (#4974) · fb223d47
      Chang Liu authored 
      * Add support for next cusparse release

* Fix lint

* Add switch and tune the performance

* Fix lint issue

* Fine tune the heuristics

* Fix lint issue

* Address comments

* Minor fix

* Address comments
      fb223d47
  27. 24 Nov, 2022 1 commit
  29. 22 Nov, 2022 2 commits
    • Ping Gong's avatar
      [Performance] Leverage hashmap to accelerate CSRSliceMatrix<kDGLCUDA, IdType> (#4924) · aa419895
      Ping Gong authored 
      

* Leverage hashmap to accelerate CSRSliceMatrix

* fix lint check

* use `min` in cuda_runtime.ch

* fix hash func

* add some comments and adjust the <grid,block> of the _SegmentMaskColKernel kernel

* set device and stream for thrust::for_each

* use thrust::cuda::par_nosync
Co-authored-by: default avatarXin Yao <xiny@nvidia.com>
      aa419895
    • Muhammed Fatih BALIN's avatar
      [Feature] (La)yer-Neigh(bor) sampling implementation (#4668) · bf264d00
      Muhammed Fatih BALIN authored 
      

* adding LABOR sampling

* add ladies and pladies samplers

* fix compile error after rebase

* add reference for ladies sampler

* Improve ladies implementation.

* weighted labor sampling initial implementation draft
fix indentation and small bug in ladies script

* importance_sampling currently doesn't work with weights

* fix weighted importance sampling

* move labor example into its own folder

* lint fixes

* Improve documentation

* remove examples from the main PR

* fix linting by not using c++17 features

* fix documentation of labor_sampler.py

* update documentation for labor.py

* reformat the labor.py file with black

* fix linting errors

* replace exception use with if

* fix typo in error comment

* fixing win64 build for ci

* fixing weighted implementation, works now.

* fix bug in the weighted case and importance_sampling==0

* address part of the reviews

* remove unused code paths from cuda

* remove unused code path from cpu side

* remove extra features of labor making use of random seed.

* fix exclude_edges bug

* remove pcg and seed logic from cpu implementation, seed logic should still work for cuda.

* minor style change

* refactor CPU implementation, take out the importance_sampling probability computation into a function.

* improve CUDAWorkspaceAllocator

* refactor importance_sampling part out to a function

* minor optimization

* fix linting issue

* Revert "remove pcg and seed logic from cpu implementation, seed logic should still work for cuda."

This reverts commit c250e07ac6d7e13f57e79e8a2c2f098d777378c2.

* Revert "remove extra features of labor making use of random seed."

This reverts commit 7f99034353080308f4783f27d9a08bea343fb796.

* fix the documentation

* disable NIDs

* improve the documentation in the code

* use the stream argument in pcg32 instead of skipping ahead t times, can discard the use of hashmap now since it is faster this way.

* fix linting issue

* address another round of reviews

* further optimize CPU LABOR sampling implementation

* fix linting error

* update the comment

* reformat

* rename and rephrase comment

* fix formatting according to new linting specs

* fix compile error due to renaming, fix linting.

* lint

* rename DGLHeteroGraph to DGLGraph to match master

* replace other occurrences of DGLHeteroGraph to DGLGraph
Co-authored-by: default avatarMuhammed Fatih BALIN <m.f.balin@gmail.com>
Co-authored-by: default avatarKaan Sancak <kaansnck@gmail.com>
Co-authored-by: default avatarQuan Gan <coin2028@hotmail.com>
      bf264d00
  31. 10 Nov, 2022 1 commit
  33. 08 Nov, 2022 1 commit
  35. 07 Nov, 2022 4 commits
  37. 06 Nov, 2022 2 commits
  39. 03 Nov, 2022 2 commits
  41. 28 Oct, 2022 1 commit
  43. 13 Oct, 2022 1 commit
  45. 11 Oct, 2022 1 commit
  47. 21 Sep, 2022 1 commit
  49. 19 Sep, 2022 1 commit
    • Xin Yao's avatar
      [Feature] Bump DLPack to v0.7 and decouple DLPack from the core library (#4454) · cded5b80
      Xin Yao authored 
      * rename `DLContext` to `DGLContext`

* rename `kDLGPU` to `kDLCUDA`

* replace DLTensor with DGLArray

* fix linting

* Unify DGLType and DLDataType to DGLDataType

* Fix FFI

* rename DLDeviceType to DGLDeviceType

* decouple dlpack from the core library

* fix bug

* fix lint

* fix merge

* fix build

* address comments

* rename dl_converter to dlpack_convert

* remove redundant comments
      cded5b80
  51. 15 Sep, 2022 1 commit
    • Xin Yao's avatar
      [Feature] Import PyTorch's CUDA stream management (#4503) · 9a00cf19
      Xin Yao authored 
      * add set_stream

* add .record_stream for NDArray and HeteroGraph

* refactor dgl stream Python APIs

* test record_stream

* add unit test for record stream

* use pytorch's stream

* fix lint

* fix cpu build

* address comments

* address comments

* add record stream tests for dgl.graph

* record frames and update dataloder

* add docstring

* update frame

* add backend check for record_stream

* remove CUDAThreadEntry::stream

* record stream for newly created formats

* fix bug

* fix cpp test

* fix None c_void_p to c_handle
      9a00cf19
  53. 06 Sep, 2022 1 commit
    • Chang Liu's avatar
      [Feature] Unify the cuda stream used in core library (#4480) · 1c9d2a03
      Chang Liu authored 
      

* Use an internal cuda stream for CopyDataFromTo

* small fix white space

* Fix to compile

* Make stream optional in copydata for compile

* fix lint issue

* Update cub functions to use internal stream

* Lint check

* Update CopyTo/CopyFrom/CopyFromTo to use internal stream

* Address comments

* Fix backward CUDA stream

* Avoid overloading CopyFromTo()

* Minor comment update

* Overload copydatafromto in cuda device api
Co-authored-by: default avatarxiny <xiny@nvidia.com>
      1c9d2a03
  55. 12 Aug, 2022 1 commit
  57. 09 Aug, 2022 1 commit
  59. 29 Jul, 2022 1 commit
    • Xin Yao's avatar
      [Feature] Add CUDA Weighted Neighborhood Sampling (#4064) · 86c81b4e
      Xin Yao authored 
      

* add weighted sampling without replacement (A-Chao)

* improve Algorithm A-Chao with block-wise prefix sum

* correctly fill out_idxs

* implement weighted sampling with replacement

* small fix

* merge host-side code of weighted/uniform sampling

* enable unit tests for cuda weighted sampling

* move thrust/cub wrapper to the cmake file

* update docs accordingly

* fix linting

* fix linting

* fix unit test

* Bump external CUB/Thrust versions

* Fix code style and update description of algorithm design

* [Feature] GPU support weighted graph neighbor sampling
commit by pengqirong(OPPO)

* merge pengqirong's implementation

* revert the change to cub and thrust

* fix linting

* use DeviceSegmentedSort for better performance

* add more comments

* add necessary notes

* add necessary notes

* resolve some comments

* define THRUST_CUB_WRAPPED_NAMESPACE

* fix doc
Co-authored-by: default avatar彭齐荣 <657017034@qq.com>
      86c81b4e
  61. 15 Jul, 2022 1 commit
  63. 27 Jun, 2022 1 commit
    • ndickson-nvidia's avatar
      [Bug][Feature] Added more missing FP16 specializations (#4140) · a5d8460c
      ndickson-nvidia authored 
      * * Added missing specializations for `__half` of `DLDataTypeTraits`, `IndexSelect`, `Full`, `Scatter_`, `CSRGetData`, `CSRMM`, `CSRSum`, `IndexSelectCPUFromGPU`
* Fixed casting issue in `_LinearSearchKernel` that was preventing it from supporting `__half`
* Added `#if`'d out specializations of `CSRGEMM`, `CSRGEAM`, and `Xgeam`, which would require functions that aren't currently provided by cublas

* * Added more specific error messages for unimplemented FP16 specializations of Xgeam, CSRGEMM, and CSRGEAM

* * Added missing instantiation of DLDataTypeTraits<__half>::dtype

* * Fixed linter error
* Added clearer comment explaining why the cast to long long is necessary

* * Worked around a compile error in some particular setup, where __half can't be constructed on the host side

* * Fixed linter formatting errors

* * Changes to comments as recommended

* * Made recommended changes to logging errors in FP16 specializations
* Also changed the existing Xgeam function for unsupported data types from LOG(INFO) to LOG(FATAL)
      a5d8460c
  65. 24 Jun, 2022 1 commit
    • nv-dlasalle's avatar
      [Performance][Optimizer] Enable using UVA and FP16 with SparseAdam Optimizer (#3885) · 020f0249
      nv-dlasalle authored 
      

* Add uva by default to embedding

* More updates

* Update optimizer

* Add new uva functions

* Expose new pinned memory function

* Add unit tests

* Update formatting

* Fix unit test

* Handle auto UVA case when training is on CPU

* Allow per-embedding decisions for whether to use UVA

* Address spares_optim.py comments

* Remove unused templates

* Update unit test

* Use dgl allocate memory for pinning

* allow automatically unpin

* workaround for d2h copy with a different dtype

* fix linting

* update error message

* update copyright
Co-authored-by: default avatarXin Yao <xiny@nvidia.com>
Co-authored-by: default avatarMinjie Wang <wmjlyjemaine@gmail.com>
      020f0249