GeezerVison

Commit history

1. Commits on Mar 11, 2026

   • CollectivePermute based allgather in host for-loop (#5963)

     Priya2698

     authored
     b4f0d0aView commit details

     Copy full SHA for b4f0d0a

     View code at this pointBrowse repository at this point
2. Commits on Feb 23, 2026

   • Add valueOrError helper for unchecked-optional-access (clang-tidy) (#5997)

     Show description for 20be631
     wujingyue

     authored
     20be631View commit details

     Copy full SHA for 20be631

     View code at this pointBrowse repository at this point
3. Commits on Feb 21, 2026

   • Signed enumerate index and related lint fixes (#5992)

     wujingyue

     authored
     fddca00View commit details

     Copy full SHA for fddca00

     View code at this pointBrowse repository at this point
4. Commits on Feb 19, 2026

   • Use std::optional instead of direct default argument for LaunchParams (#5980)

     Show description for bda6c6a
     rdspring1

     authored
     bda6c6aView commit details

     Copy full SHA for bda6c6a

     View code at this pointBrowse repository at this point
5. Commits on Feb 5, 2026

   • Add number_of_streams binding to MultiDeviceExecutor (#5916)

     nsarka

     authored
     20d9b3aView commit details

     Copy full SHA for 20d9b3a

     View code at this pointBrowse repository at this point
6. Commits on Jan 27, 2026

   • Add PDL to normalization schedulers (#5548)

     Show description for 9985742
     rdspring1

     authored
     9985742View commit details

     Copy full SHA for 9985742

     View code at this pointBrowse repository at this point
7. Commits on Jan 22, 2026

   • Move unique_ptr<Fusion> to FusionExecutorCache (#5856)

     Show description for fb1f96c
     rdspring1

     authored
     fb1f96cView commit details

     Copy full SHA for fb1f96c

     View code at this pointBrowse repository at this point
8. Commits on Jan 21, 2026

   • Clean up includes and rename utils to base (#5852)

     Show description for 0c147ae
     wujingyue

     authored
     0c147aeView commit details

     Copy full SHA for 0c147ae

     View code at this pointBrowse repository at this point

   • Rename log_sumexp to logsumexp (#5849)

     wujingyue

     authored
     af00238View commit details

     Copy full SHA for af00238

     View code at this pointBrowse repository at this point
9. Commits on Jan 20, 2026

   • GroupedBlockQuantizeOp PR2: Adding python API and updating llama4 benchmark (#5777)

     Show description for 2760470
     jjsjann123

     authored
     2760470View commit details

     Copy full SHA for 2760470

     View code at this pointBrowse repository at this point

   • Explicit Interstream sync (#5838)

     Show description for 6580d3a
     samnordmann

     authored
     6580d3aView commit details

     Copy full SHA for 6580d3a

     View code at this pointBrowse repository at this point
10. Commits on Jan 13, 2026

    • Add TensorView-based shard_tensor API and refactor tests (#5791)

      Show description for 130d3f4
      

      wujingyue

      and

      greptile-apps[bot]

      authored
      130d3f4View commit details

      Copy full SHA for 130d3f4

      View code at this pointBrowse repository at this point

    • Data and tensor parallel MLP (#5786)

      wujingyue

      authored
      06b388fView commit details

      Copy full SHA for 06b388f

      View code at this pointBrowse repository at this point
11. Commits on Jan 12, 2026

    • Rename schedule_3D to schedule_3d (#5789)

      Show description for d15383c
      wujingyue

      authored
      d15383cView commit details

      Copy full SHA for d15383c

      View code at this pointBrowse repository at this point
12. Commits on Jan 10, 2026

    • Use `toPolymorphicValue` to convert `py::handle` directly to `PolymorphicValue` (#5771)

      Show description for 5ae31f2
      rdspring1

      authored
      5ae31f2View commit details

      Copy full SHA for 5ae31f2

      View code at this pointBrowse repository at this point

    • Add simple warp specialized example to direct bindings. (#5683)

      Show description for 657bf61
      rdspring1

      authored
      657bf61View commit details

      Copy full SHA for 657bf61

      View code at this pointBrowse repository at this point
13. Commits on Jan 8, 2026

    • Add Cutlass MxFp8 Block Scale Matrix Multiplication (#5736)

      Show description for 463dfba
      rdspring1

      authored
      463dfbaView commit details

      Copy full SHA for 463dfba

      View code at this pointBrowse repository at this point
14. Commits on Jan 6, 2026

    • [Host irs / stream lowering] Broadcast based pipeline (#5621)

      Show description for 84fb3b2
      samnordmann

      authored
      84fb3b2View commit details

      Copy full SHA for 84fb3b2

      View code at this pointBrowse repository at this point

    • Reference implementation for triangle updates (#5732)

      Show description for a88bfb1
      

      wujingyue

      and

      greptile-apps[bot]

      authored
      a88bfb1View commit details

      Copy full SHA for a88bfb1

      View code at this pointBrowse repository at this point
15. Commits on Jan 5, 2026

    • Add bias and mask support to SdpaFwdOp (#5663)

      wujingyue

      authored
      1db87d1View commit details

      Copy full SHA for 1db87d1

      View code at this pointBrowse repository at this point
16. Commits on Dec 13, 2025

    • Create LRU cache for direct bindings. (#4893)

      Show description for fe23484
      rdspring1

      authored
      fe23484View commit details

      Copy full SHA for fe23484

      View code at this pointBrowse repository at this point
17. Commits on Dec 2, 2025

    • Python bindings for block quantization (#5591)

      Show description for 9bd8c34
      

      authored
      9bd8c34View commit details

      Copy full SHA for 9bd8c34

      View code at this pointBrowse repository at this point
18. Commits on Nov 26, 2025

    • Add TensorView inner/outer split aliases (#5595)

      Show description for 00f626d
      wujingyue

      authored
      00f626dView commit details

      Copy full SHA for 00f626d

      View code at this pointBrowse repository at this point
19. Commits on Nov 13, 2025

    • Add DataType::Index to python reproducer (#5509)

      Show description for c209913
      rdspring1

      authored
      c209913View commit details

      Copy full SHA for c209913

      View code at this pointBrowse repository at this point

    • Fix python reproducer for dynamic broadcast_in_dim (#5508)

      Show description for e5d9af5
      rdspring1

      authored
      e5d9af5View commit details

      Copy full SHA for e5d9af5

      View code at this pointBrowse repository at this point
20. Commits on Nov 10, 2025

    • Create `test_tutorial_scheduling_layer_norm_with_profiling` (#5481)

      Show description for e2c162f
      rdspring1

      authored
      e2c162fView commit details

      Copy full SHA for e2c162f

      View code at this pointBrowse repository at this point
21. Commits on Nov 9, 2025

    • Modify heuristic parameters before scheduling fusion in direct bindings. (#5485)

      Show description for c64c14c
      rdspring1

      authored
      c64c14cView commit details

      Copy full SHA for c64c14c

      View code at this pointBrowse repository at this point
22. Commits on Oct 31, 2025

    • Factor multi-device execution helpers into execution_utils (#5461)

      Show description for 75d5084
      wujingyue

      authored
      75d5084View commit details

      Copy full SHA for 75d5084

      View code at this pointBrowse repository at this point
23. Commits on Oct 29, 2025

    • Add support for automatic scheduler in direct bindings (#5374)

      Show description for c8d9084
      rdspring1

      authored
      c8d9084View commit details

      Copy full SHA for c8d9084

      View code at this pointBrowse repository at this point
24. Commits on Oct 21, 2025

    • exposing layout op at direct python binding (#5345)

      Show description for 7ee0a94
      jjsjann123

      authored
      7ee0a94View commit details

      Copy full SHA for 7ee0a94

      View code at this pointBrowse repository at this point
25. Commits on Oct 17, 2025

    • fp4 packed dtype support on direct python API (#5380)

      Show description for 95c857f
      jjsjann123

      authored
      95c857fView commit details

      Copy full SHA for 95c857f

      View code at this pointBrowse repository at this point

    • Allocate CUPTI buffer dynamically (#5402)

      Show description for 79cdcab
      Priya2698

      authored
      79cdcabView commit details

      Copy full SHA for 79cdcab

      View code at this pointBrowse repository at this point

    • Update benchmark_utils.py, pytorch_utils.py, and profile.cpp for benchmarking (#5395)

      Show description for e69129c
      rdspring1

      authored
      e69129cView commit details

      Copy full SHA for e69129c

      View code at this pointBrowse repository at this point

    • Use std::unique_ptr for DeviceMesh and FusionExecutorCache in direct bindings (#5311)

      Show description for cf04bc0
      rdspring1

      authored
      cf04bc0View commit details

      Copy full SHA for cf04bc0

      View code at this pointBrowse repository at this point
26. Commits on Oct 14, 2025

    • Add CUPTI profiling to direct bindings (#5324)

      Show description for 6219364
      rdspring1

      authored
      6219364View commit details

      Copy full SHA for 6219364

      View code at this pointBrowse repository at this point