NVIDIA/cutlass
1
0
Fork 0
mirror of https://github.com/NVIDIA/cutlass.git synced 2026-05-12 09:15:56 +00:00
Code Issues Packages Projects Releases Wiki Activity
836 Commits 21 Branches 52 Tags
c213bfdfc1f4ffb156c69d51d07efcf7f367f2fb
Commit Graph

197 Commits

Author SHA1 Message Date
Junkai-Wu
c213bfdfc1 Remove redundant dsl examples. (#3071) 2026-02-25 22:42:01 -05:00
Linfeng Zheng
3476ddb7bd remove mixed_input_fmha_prefill (#3041) 2026-02-18 07:59:01 -05:00
Yihan Chen
291300ffff [CuTeDSL] implment a cta-level norm example (both layernorm and rmsnorm) (#3009) 
* kernel impl

* add copyright
 2026-02-14 17:54:03 +08:00
aragorn-guan
f9a5f76b7a Replace fence proxy to the latest routine code in examples/distributed/all_reduce_tma.py (#3027) 2026-02-14 17:51:20 +08:00
Junkai-Wu
d4bbf728ca v4.4 tag release update. (#3032) 2026-02-13 23:27:58 -05:00
aragorn-guan
8dbce01473 [CuTeDSL] Distributed example, using TMA load to access remote memory rank-by-rank, reducing in cta, broadcast result to all ranks by multimem TMA store (#2970) 2026-02-11 11:54:00 +08:00
drazi
71aa7a0abc Merge pull request #2919 from pbelevich/patch-1 
Refactor binary_op functions to remove unused result parameter
 2026-02-11 11:48:58 +08:00
Junkai-Wu
6b3e607b85 v4.4 release update v2. (#2999) 2026-02-03 20:48:31 -05:00
Hua Huang
1cfbb53a23 [CuTeDSL] Fix: SM100 block-scale gemm overlapping accumulator (#2995) 
* Fix: SM100 block-scale gemm overlapping accumulator

Signed-off-by: Hua Huang <huah@nvidia.com>

* Also include threads_per_warp fix

Signed-off-by: Hua Huang <huah@nvidia.com>

---------

Signed-off-by: Hua Huang <huah@nvidia.com>
 2026-02-03 11:01:41 +08:00
dongxiao
a4eb0e05f6 fix performance inssues in cute-dsl examples for 4.4-ctk13.1 release (#2988) 
* fix grouped gemm

* fix mixed input gemm

* fix mixed input grouped gemm

* fix version checking

* use advanced compiler options

* fix comment

* rename advanced compiler configs to adcanced compiler control

* fix comment

* fix name

* fix name
 2026-01-30 13:31:04 +08:00
myu-guo
d252b01300 fix performance regression in cute-dsl examples for 4.4-ctk13.1 release (#2990) 
* fix regression with cu13.1

* update
 2026-01-30 13:30:49 +08:00
Xiao Song
acb45938e9 Update nvvm API call from nvvm enum to str (#2985) 2026-01-27 17:28:29 +08:00
Xiao Song
7a14467776 update api usage (#2969) 2026-01-27 15:33:22 +08:00
Junkai-Wu
9fba3195f9 v4.4 update. (#2979) 2026-01-24 11:46:17 -05:00
Johnsonms
0edaa6e47d Fix out-of-bounds TMA access in wgmma_tma_sm90 tutorial (#2945) 2026-01-23 12:54:12 +08:00
Aidan Do
431d070fcb [docs] Add additional tip for generating less kernels in blockwise (#2940) 
- Running without this generates a lot of kernels
- Clarified CMake configuration for selecting GEMM kernels and added details on kernel generation granularity.
 2026-01-23 12:53:51 +08:00
Brian K. Ryu
147f5673d0 New RMS Norm example with unit tests (#2917) 
* Add rmsnorm example

* Address reviewer comments. (1) use the cute.runtime definition directly. (2) use the nvvm_wrapper's warp reduce directly

* Separate out reduce.py

* Change copyright notice years
 2026-01-13 09:05:31 +08:00
Johnsonms
8c52459504 Fix incorrect tensor layout strides in Blackwell MMA tutorial comments (#2921) 2026-01-09 01:02:41 -05:00
Junkai-Wu
0d2b201e8c v4.3.5 update. (#2934) 
* v4.3.5 update.

* Update copyright to 2026
 2026-01-08 15:02:56 -05:00
Andrew Yooeun Chun
eb61c91147 Fix CUDA version checking in examples (#2894) 
* examples: update CUDA version requirements in Blackwell examples

* examples: fix comments to specify the correct CUDA version requirement
 2026-01-07 00:20:37 -05:00
Aidan Do
670480df3a Fix SFB Layout scale granularity representation (#2924) 2026-01-06 23:55:21 -05:00
Pavel Belevich
b6d7703e02 Refactor binary_op functions to remove unused result parameter 2026-01-02 11:23:43 -05:00
Pavel Belevich
f9bedd9096 Fix print statement for floor division result 2026-01-02 11:15:15 -05:00
questa-quan-wang
3f4c086d09 new example with TMA prefetch feature targeting for DRAM latency bound cases (#2881) 
Co-authored-by: Questa Wang <questaw@computelab-frontend-7.nvidia.com>
 2025-12-23 15:29:48 +08:00
Junkai-Wu
7f5fe3edf1 v4.3.4 update. (#2892) 2025-12-21 11:49:12 -05:00
dongxiao
331e2f451c add missing condition for sync (#2889) 2025-12-19 11:00:30 +08:00
Linfeng Zheng
f6402fcd5e add pytest support for tutorial gemm (#2826) 
* add pytest support for tutorial gemm

* add license
 2025-12-05 08:45:01 -05:00
bangyu shen
7252a2d17e remove internal comment (#2841) 
Co-authored-by: bangyus <bangyus@nvidia.com>
 2025-12-04 10:36:21 -05:00
Junkai-Wu
bc680c7f67 v4.3.2 update. (#2839) 2025-12-04 10:14:32 -05:00
bangyu shen
52ae719eda [examples][CuTeDSL] init commit for distirbuted examples (#2806) 
* init commit for distirbuted examples

* better OOB protection

* and try import to nvshmem for better error message and a READMME.md to introduce nvshmem and multimem instructions

* add some lamport explanation

* enhance f8 output and warn that f8 output can have nan in it

* tell user why we need complicate data conversions in ref check part

* tell user we don't support nvshmem device function

---------

Co-authored-by: bangyus <bangyus@nvidia.com>
 2025-12-01 22:25:40 -05:00
drazi
ec8daf642d Merge pull request #2809 from whatdhack/patch-1 
Update notebook title from 'Tour to' to 'Tour of'
 2025-11-28 18:07:34 +08:00
Fung Xie
286781a1fb add requirements.txt 2025-11-27 17:02:27 -08:00
Fung Xie
2664cac685 enhanced the example for tvm-ffi 2025-11-27 17:02:26 -08:00
Fung Xie
b9154d65b3 update examples for tvm-ffi 2025-11-27 17:02:26 -08:00
Fung Xie
afe2f71522 reorganize examples for tvm-ffi 2025-11-27 17:02:26 -08:00
Fung Xie
739fffce27 fix TVM FFI doc and update example 2025-11-27 17:02:26 -08:00
Junkai-Wu
1de3a576cc v4.3.1 update. (#2817) 2025-11-27 09:49:30 -05:00
Shreya Gaur
2052fd3885 Blockscaled Ragged Contiguous Grouped Gemm for MoEs (#2790) 
* Adding blockscaled ragged contiguous grouped gemm for MoEs

* cleaning up the example

* introduction to example improved

---------

Co-authored-by: Shreya Gaur <shgaur@dc2-container-xterm-012.prd.it.nvidia.com>
 2025-11-26 20:16:49 -05:00
whatdhack
4a55379686 Update notebook title from 'Tour to' to 'Tour of' 
Grammar check . LLM's can quickly clean up such issues.
 2025-11-24 20:11:14 -08:00
Junkai-Wu
8cd5bef43a v4.3 tag release update. (#2789) 2025-11-20 20:49:44 -05:00
Linfeng Zheng
406e078b29 add a notebook for tour to sol gemm (#2780) 
* add tour to sol gemm notebook

* change some typos

* change some typos
 2025-11-20 09:41:01 -05:00
Mindy Li
06b6bd7d7b remove cute dsl pdl example. 2025-11-09 21:47:00 -08:00
Linfeng Zheng
2252254ce2 Add tutorial fp16_gemm_1 (#2750) 
* Add tutorial fp16_gemm_1

* refine

* refine

* refine

* revert changes in fp16_gemm_0.py
 2025-11-06 22:40:09 -05:00
Ali Hassani
d1ef0e87f2 DistGEMM bug fixes (#2713) 
* Blackwell DistGEMM bug fixes

1. If using preferred cluster, there needs to be a branch so that
   the universal GEMM wrapper finds the correct base params.
2. Workspace sizes can change depending on problem shape in Blackwell,
   and DistGEMM was previously using the per-device shape to evaluate
   workspace size instead of the per-gemm shape.
3. Flattened size used to initialize host tensors can overflow (in
   Hopper example as well)
4. Preferred and fallback cluster args need to be set explicitly,
   otherwise if someone modifies the example to use preferred cluster,
   it will just fail.

* Fix example runtimes

* Set default fallback cluster shapes to the static ones
 2025-11-06 13:31:24 -05:00
ANIKET SHIVAM
020c700e97 support for K=0 for sm100 GG (#2746) 2025-11-04 11:25:39 -05:00
Junkai-Wu
b1d6e2c9b3 v4.3 update. (#2709) 
* v4.3 update.

* Update the cute_dsl_api changelog's doc link

* Update version to 4.3.0

* Update the example link

* Update doc to encourage user to install DSL from requirements.txt

---------

Co-authored-by: Larry Wu <larwu@nvidia.com>
 2025-10-21 14:26:30 -04:00
Aya Z. Ibrahim
64579189ec Feature/add bottom causal mask (#2480) 
* Rebase to latest

* update

* upd

Summary:

Test Plan:

Reviewers:

Subscribers:

Tasks:

Tags:

* Update fmha_fusion.hpp

* Update fmha_fusion.hpp

fixed flipped logic for isQBegin

* Update fmha_fusion.hpp

* Avoid use of booleans

The current expression is confusing

* fmt

* Update fmha_fusion.hpp

Reproduce error/fix with: 
./77_blackwell_fmha_fp16 --verify --b=1 --q=1013 --k=1024 --h=1 --h_k=1 --mask=causal --causal-type=qend

* add test, format

---------

Co-authored-by: Richard Cai <ricai@nvidia.com>
Co-authored-by: Haicheng Wu <57973641+hwu36@users.noreply.github.com>
 2025-09-18 17:11:23 -04:00
Junkai-Wu
74825181f2 Remove old-version dsl examples. (#2644) 2025-09-17 22:23:30 -04:00
Junkai-Wu
6a35b4d22f v4.2 tag release. (#2638) 2025-09-15 12:21:53 -04:00
Richard Cai
56f0718a97 ex77 backwards GQA (#2556) 
* bwd GQA init

* Update examples/77_blackwell_fmha/77_blackwell_fmha_bwd.cu

* ref kernel type conversion fix

---------

Co-authored-by: Haicheng Wu <57973641+hwu36@users.noreply.github.com>
 2025-09-09 12:53:28 -04:00