yukuai26
8dfa329827
Grouped GEMM skip useless computation for unaligned Ms ( #103 )
...
* Grouped GEMM skip useless computation for unaligned Ms
* Update readme.md
* small typo
* Rename variables
* Restore previous indent
* Format
* Refactor tests
* Add `SkipComputation` types
* Bug fixed
* Format
* Fix tests
* Add assertions
* Minor fix
---------
Co-authored-by: yukuai <yukuai@deepseek.com >
Co-authored-by: Chenggang Zhao <chenggangz@deepseek.com >
2025-05-27 13:43:38 +08:00
Chenggang Zhao
350989eef3
Unify ceil_divs
2025-05-15 16:48:32 +08:00
Zhean Xu
04278f6dee
Weight gradient kernels for dense and MoE models ( #95 )
...
* Init weight gradient kernels.
* Support unaligned n,k and gmem stride
* Update docs
* Several cleanups
* Remove restrictions on N
* Add stride(0) assertions
---------
Co-authored-by: Chenggang Zhao <chenggangz@deepseek.com >
2025-05-14 14:47:58 +08:00
Gabriel Wu
bfe983c4c2
Refactor JIT compilation (+NVRTC support) ( #94 )
...
* [wip] refactor: compile to .cubin
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com >
* refactor: compile to .cubin and add NVRTC option
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com >
* fix: compiler version
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com >
* feat: compat for old drivers
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com >
* feat: save kernel name to file
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com >
* feat: fix win compat
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com >
* fix: windows compat
Signed-off-by: Gabriel Wu <13583761+lucifer1004@users.noreply.github.com >
* feat: make API more general
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com >
* feat: drop support for CUDA<12.3
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com >
* doc: update README
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com >
* Some lints and refactor
* Refactor runtime
* Several fixes
* Refactor environment variables
* Code format
* Add a TODO
* Compatible with CUDA 12.3
* Fix indent
* Fix typing
* Drop support for Windows
* Add a TODO
---------
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com >
Signed-off-by: Gabriel Wu <13583761+lucifer1004@users.noreply.github.com >
Co-authored-by: Chenggang Zhao <chenggangz@deepseek.com >
2025-05-07 11:38:14 +08:00
yukuai26
891f35adf5
Support TMA multicast on B with m_grouped_gemm_contiguous. ( #88 )
2025-04-21 09:43:17 +08:00
ademeure
6cbff5778f
Correctly flush L2, as reconstructing the tensors on every iteration effectively put them in the L2, and gave the GPU enough idle time to avoid thermal throttling in a potentially unrealistic way.
...
The previous behaviour is potentially representative of some use cases (e.g. previous kernel filling L2 with the data in a very specific way) but not standard benchmarking practice.
2025-03-15 20:46:24 +00:00
Chenggang Zhao
39c10e6c31
Revert "Merge pull request #49 from A-transformer/maximum_fp8_e4m3_value"
...
This reverts commit 4d4f2342fe9d3222a93e
2025-03-10 09:47:02 +08:00
A-transformer
629857685e
Maximum representable value in FP8 E4M3 format
...
Replace Hardcoded 448.0 with Global Constant FP8_E4M3_MAX for FP8 E4M3 Format
2025-03-07 19:58:02 +04:00
AcraeaTerpsicore
96b31fd6bb
fix typo
2025-02-26 18:37:22 +08:00
xuzhean
bc989405fe
fix: prevent expected_m from exceeding m in test_core
2025-02-26 16:55:47 +08:00
Chenggang Zhao
a6d97a1c1b
Initial commit
2025-02-25 22:52:41 +08:00
