leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 27 Packages Projects Releases Wiki Activity

v4.1 release update v2. (#2481)

Browse Source
This commit is contained in:
Junkai-Wu
2025-07-21 22:03:55 -04:00
committed by GitHub
parent 9baa06dd57
commit fd6cfe1ed0
179 changed files with 7878 additions and 1286 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/41_fused_multi_head_attention/gemm/find_default_mma.h
+2 -2
View File
@@ -31,7 +31,7 @@
/*! \file
\brief Cutlass provides helper template functions to figure out the right
datastructures to instanciate to run a GEMM with various parameters (see
datastructures to instantiate to run a GEMM with various parameters (see
`cutlass/gemm/threadblock/default_mma.h`). However, due to template
instantiation priority rules, it will only create an MmaMultiStage with
kStages=3 (otherwise creates an MmePipelined - which is not compatible with
@@ -83,7 +83,7 @@ template <
typename InstructionShape,
/// Number of stages used in the pipelined mainloop
int Stages,
/// Operation perfomed by GEMM
/// Operation performed by GEMM
typename Operator,
typename Enable_ = void>
struct FindDefaultMma {
examples/41_fused_multi_head_attention/gemm/mma_from_smem.h
+1 -1
View File
@@ -522,7 +522,7 @@ class MmaPipelinedFromSharedMemory : public MmaBaseFromSharedMemory<
// For API compatibility with MmaMultistageFromSharedMemory
// but not supported as it worsens perf: older gpus < sm80 don't
// support async tranfers and have to waste registers
// support async transfers and have to waste registers
CUTLASS_DEVICE
void set_prologue_done(bool value) {}
CUTLASS_DEVICE