Online softmax is disabled on the fly #153241
Labels
module: inductor
oncall: pt2
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
🐛 Describe the bug
Hi there, I started getting this warning when running a
torch.compile()'d transformer forward inference pass withmode="reduce-overhead", fullgraph=TrueI noticed this appears to be a TODO? https://github.com/pytorch/pytorch/blame/main/torch/_inductor/lowering.py#L7058C50-L7058C50
So I guess to whom it may concern, perhaps @shunting314, it does appear that inference needs split online softmax.
Versions
Collecting environment information...
PyTorch version: 2.7.0+cu128
Is debug build: False
CUDA used to build PyTorch: 12.8
ROCM used to build PyTorch: N/A
OS: Ubuntu 24.04.1 LTS (aarch64)
GCC version: (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0
Clang version: Could not collect
CMake version: version 3.28.3
Libc version: glibc-2.39
Python version: 3.12.3 (main, Feb 4 2025, 14:48:35) [GCC 13.3.0] (64-bit runtime)
Python platform: Linux-6.8.0-1013-nvidia-64k-aarch64-with-glibc2.39
Is CUDA available: True
CUDA runtime version: 12.8.93
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA GH200 480GB
Nvidia driver version: 570.86.16
cuDNN version: Probably one of the following:
/usr/lib/aarch64-linux-gnu/libcudnn.so.9.8.0
/usr/lib/aarch64-linux-gnu/libcudnn_adv.so.9.8.0
/usr/lib/aarch64-linux-gnu/libcudnn_cnn.so.9.8.0
/usr/lib/aarch64-linux-gnu/libcudnn_engines_precompiled.so.9.8.0
/usr/lib/aarch64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.8.0
/usr/lib/aarch64-linux-gnu/libcudnn_graph.so.9.8.0
/usr/lib/aarch64-linux-gnu/libcudnn_heuristic.so.9.8.0
/usr/lib/aarch64-linux-gnu/libcudnn_ops.so.9.8.0
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: aarch64
CPU op-mode(s): 64-bit
Byte Order: Little Endian
CPU(s): 64
On-line CPU(s) list: 0-63
Vendor ID: ARM
Model name: Neoverse-V2
Model: 0
Thread(s) per core: 1
Core(s) per cluster: 64
Socket(s): -
Cluster(s): 1
Stepping: r0p0
BogoMIPS: 2000.00
Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm ssbs sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh bti
NUMA node(s): 9
NUMA node0 CPU(s): 0-63
NUMA node1 CPU(s):
NUMA node2 CPU(s):
NUMA node3 CPU(s):
NUMA node4 CPU(s):
NUMA node5 CPU(s):
NUMA node6 CPU(s):
NUMA node7 CPU(s):
NUMA node8 CPU(s):
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; __user pointer sanitization
Vulnerability Spectre v2: Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] numpy==2.2.5
[pip3] torch==2.7.0+cu128
[pip3] torchao==0.10.0
[pip3] triton==3.3.0
[conda] Could not collect
cc @chauhang @penguinwu @voznesenskym @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @chenyang78 @kadeng @muchulee8 @amjames @aakhundov
The text was updated successfully, but these errors were encountered: