-
Notifications
You must be signed in to change notification settings - Fork 21.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
triton
package that ships with torch is not compatible with torch.ops.matmul
#125539
Comments
"No module named 'nvi'" means that there's a version mismatch. Are you able to run your triton code in eager mode (without torch.compile)? |
yes, in the minimal repro I provided, the code first runs the kernel without compile first. Only errors out when compiling. |
@jeromeku looking at your relevant libraries, i see you have both triton and pytorch-triton installed, could you pip uninstall triton so that there's only one triton? |
I tried to do that, but uninstalling
|
That's because ops is likely not defined in the
notice that there's no torch compile anymore, still runs into the same autotuner issue. I suspect the triton package that ships with torch is not compatible with torch.ops.matmul. I'll update the issue, for proper triage. |
torch.compile
error with user-defined kernel: "No module named 'nvi'" triton
package that ships with torch is not compatible with torch.ops.matmul
I have the same issue and will update more details later |
UPDATE from @oulgen:
with triton distributed via torch does not work without compile.
🐛 Describe the bug
@oulgen
Per the title,
torch.dynamo
errs out with "No module named 'nvi'" when compiling a user-defined kernel.A minimal repro is below, where the "user-defined kernel" is simply
triton.ops.matmul
, the officialtriton
matmul implementation:torch version:
2.4.0.dev20240427+cu118
triton version:
3.0.0
Full versions pasted in box below.
Full error:
Versions
Collecting environment information...
PyTorch version: 2.4.0.dev20240427+cu118
Is debug build: False
CUDA used to build PyTorch: 11.8
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.2 LTS (x86_64)
GCC version: (Ubuntu 11.3.0-1ubuntu1~22.04.1) 11.3.0
Clang version: Could not collect
CMake version: version 3.27.20230625-g7e38674
Libc version: glibc-2.35
Python version: 3.11.8 (main, Feb 26 2024, 21:39:34) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.19.0-45-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 11.8.89
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA RTX A6000
Nvidia driver version: 525.116.04
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.2
/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.2
/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.2
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.2
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.2
/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.2
/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.2
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 46 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 8
On-line CPU(s) list: 0-7
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Gold 5315Y CPU @ 3.20GHz
CPU family: 6
Model: 106
Thread(s) per core: 1
Core(s) per socket: 8
Socket(s): 1
Stepping: 6
BogoMIPS: 6405.68
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single pti ibpb fsgsbase bmi1 avx2 smep bmi2 invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves umip pku ospke vaes vpclmulqdq rdpid
Hypervisor vendor: Xen
Virtualization type: full
L1d cache: 384 KiB (8 instances)
L1i cache: 256 KiB (8 instances)
L2 cache: 10 MiB (8 instances)
L3 cache: 96 MiB (8 instances)
NUMA node(s): 1
NUMA node0 CPU(s): 0-7
Vulnerability Itlb multihit: KVM: Mitigation: VMX unsupported
Vulnerability L1tf: Mitigation; PTE Inversion
Vulnerability Mds: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Meltdown: Mitigation; PTI
Vulnerability Mmio stale data: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Retbleed: Not affected
Vulnerability Spec store bypass: Vulnerable
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Retpolines, IBPB conditional, STIBP disabled, RSB filling, PBRSB-eIBRS Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] numpy==1.26.4 (envs/lib/python3.11/site-packages)
[pip3] pytorch-triton==3.0.0+45fff310c8 (envs/lib/python3.11/site-packages)
[pip3] torch==2.4.0.dev20240427+cu118 (envs/lib/python3.11/site-packages)
[pip3] torchao==0.1 (/notebooks/Triton/ao)
[pip3] triton==3.0.0 (envs/lib/python3.11/site-packages)
[conda] numpy 1.26.4 pypi_0 pypi
[conda] pytorch-triton 3.0.0+45fff310c8 pypi_0 pypi
[conda] torch 2.4.0.dev20240427+cu118 pypi_0 pypi
[conda] torchao 0.1 dev_0
[conda] triton 3.0.0 pypi_0 pypi
cc @malfet @seemethere @ptrblck @msaroufim
The text was updated successfully, but these errors were encountered: