Enlarge init range.#74

Closed

vickiw973 wants to merge 187 commits into

gpu-mode:mainfrom

vickiw973:feature/change_to_use_cute

Commits on Feb 18, 2025

first commit
Mark Saroufim
committed

Commits on Feb 20, 2025

Main Practice Problems
Mark Saroufim
committed

Commits on Feb 21, 2025

update beta.yaml
Mark Saroufim
committed
Fix: eval/utils paths in task
S1ro1
committed

Commits on Feb 22, 2025

Updates to Grayscale
Mark Saroufim
committed
update
Mark Saroufim
committed
Fix: vectorsum desc
S1ro1
committed
Vectorsum: more sizes
S1ro1
committed
grayscale
Mark Saroufim
committed
Vectorsum
S1ro1
committed
Update sorting problem
Mark Saroufim
committed
Vectoradd
S1ro1
committed
Minor fixes to matmul
Mark Saroufim
committed
Vectoradd
S1ro1
committed
convolution is bueno
Mark Saroufim
committed

Commits on Feb 23, 2025

Merge pull request #4 from gpu-mode/vectoradd
Mark Saroufim
authored
prefixsum
Mark Saroufim
committed
remove useless comments
Mark Saroufim
committed
Make solution more robust to cheese solutions by adding scale and offset
Mark Saroufim
committed
Merge pull request #3 from gpu-mode/dev-siro
Mark Saroufim
authored
fixed prefixsum
Mark Saroufim
committed
Merge pull request #2 from gpu-mode/dev
Mark Saroufim
authored
improvements to allclose:
ngc92
committed
simplified reference utility
ngc92
committed
reduce in fp64
ngc92
committed
Merge pull request #6 from gpu-mode/ngc92/improvements
S1ro1
authored
histogram:
ngc92
committed
Merge pull request #7 from gpu-mode/ngc92/histogram
Mark Saroufim
authored
Change sizes on conv2d
S1ro1
committed
Merge pull request #9 from gpu-mode/fix/smaller-conv2d
ngc92
authored
model solutions
ngc92
committed
use double for reference calculation
ngc92
committed
comment
ngc92
committed
Merge pull request #10 from gpu-mode/ngc92/problems
Mark Saroufim
authored
Feat: templates

S1ro1
authored and
ngc92
committed
fixup
ngc92
committed

Commits on Mar 3, 2025

Update README.md with Docs Links
alexzhang13
authored

Commits on Apr 9, 2025

Update submission_cuda_inline.py
Mark Saroufim
authored
Merge pull request #14 from gpu-mode/msaroufim-patch-1
Mark Saroufim
authored

Commits on Apr 15, 2025

Commits on Apr 16, 2025

Update FP8MM (#22)
ngc92
authored

Commits on Apr 30, 2025

Correct shape of a_scale + b_scale
mreso
committed
Merge pull request #26 from mreso/fix/fp8_description
Mark Saroufim
authored

Commits on May 1, 2025

Feat: enlarge task timeout for moe
S1ro1
authored

Commits on May 10, 2025

Update README.md
Mark Saroufim
authored

Commits on May 12, 2025

update eval file to allow pt profiling
ngc92
committed

Commits on May 13, 2025

update eval file to put an upper bound on total benchmark duration
ngc92
committed

Commits on May 17, 2025

Commits on May 18, 2025

Update template-hip.py
Mark Saroufim
authored
Merge pull request #33 from gpu-mode/msaroufim-patch-2
Mark Saroufim
authored

Commits on May 19, 2025

add MLA problem
alexzhang13
committed
Merge pull request #34 from gpu-mode/amd/mla
Mark Saroufim
authored
add mla problem
Mark Saroufim
committed

Commits on May 20, 2025

Update amd.yaml
msaroufim
authored

Commits on May 22, 2025

Commits on May 23, 2025

Commits on May 25, 2025

adjust mla atol
danielhua23
committed

Commits on May 26, 2025

Merge pull request #41 from danielhua23/main
alexzhang13
authored
Create LICENSE
Mark Saroufim
authored

Commits on Jun 2, 2025

Commits on Jun 5, 2025

Commits on Jun 16, 2025

Commits on Jun 18, 2025

Commits on Jul 2, 2025

Update README.md
alexzhang13
authored

Commits on Jul 17, 2025

PMPP v2

Mark Saroufim
authored and
ngc92
committed
problem updates
ngc92
committed
refactor
ngc92
committed

Commits on Aug 9, 2025

Merge pull request #49 from gpu-mode/ngc92/pmppv2
Mark Saroufim
authored
v2 name suffix
Mark Saroufim
committed
add b200 for pmppv2
Mark Saroufim
committed

Commits on Aug 20, 2025

Commits on Aug 25, 2025

Commits on Aug 26, 2025

Feat: conform to kernelbot infrastructure
S1ro1
committed

Commits on Aug 27, 2025

Commits on Aug 28, 2025

Commits on Aug 29, 2025

fix import
ngc92
committed
Merge pull request #54 from gpu-mode/ngc92/fix
Mark Saroufim
authored

Commits on Aug 30, 2025

Commits on Sep 1, 2025

Commits on Sep 2, 2025

add reference impl of gemm-reducescatter
Xun Wang
committed

Commits on Sep 3, 2025

Commits on Sep 8, 2025

typo fix
Xun Wang
committed
remove transposed_weight bool variable
Xun Wang
committed
update custom_kernel and yaml doc
Xun Wang
committed
add has_bias in test spec
Xun Wang
committed

Commits on Sep 9, 2025

clarify rules
danielhua23
committed
clarify rules
danielhua23
committed
Merge pull request #61 from danielhua23/a2a_rule_clarify
Mark Saroufim
authored

Commits on Sep 10, 2025

Update deadline for amd-identity problem
Mark Saroufim
authored
update test and benchmark shapes
Xun Wang
committed

Commits on Sep 11, 2025

change dtype
Xun Wang
committed
Use events for pmpp_v2 benchmarking
achalpandeyy
committed
Merge pull request #62 from achalpandeyy/fix_pmppv2_benchmarking
Mark Saroufim
authored

Commits on Sep 12, 2025

Feat: works
S1ro1
committed

Commits on Sep 14, 2025

Commits on Sep 21, 2025

add allgather gemm reference implementation
Xun Wang
committed

Commits on Sep 22, 2025

use rand in data generator
Xun Wang
committed

Commits on Sep 24, 2025

Feat: works
S1ro1
committed

Commits on Sep 27, 2025

Increase timeouts as temporary solution to Cauchy distribution overhead
alexzhang13
authored

Commits on Sep 28, 2025

Commits on Oct 12, 2025

tmp: increase timeout
S1ro1
committed

Commits on Oct 13, 2025

Change deadlines to 2025-10-15 for AMD problems
S1ro1
authored

Commits on Oct 14, 2025

Commits on Oct 15, 2025

fix getting of input dimensions in pmpp_v2/prefixsum_py
achalpandeyy
committed

Commits on Oct 16, 2025

Merge pull request #71 from achalpandeyy/fix_prefixsumv2
Mark Saroufim
authored

Commits on Nov 1, 2025

Fix reference for matmul_py
alexzhang13
authored

Commits on Nov 10, 2025

Commits on Nov 11, 2025