OS Manuals

/usr/bin/flashinfer

python3.12 version of vllm

From py3.12-vllm-cuda-12.4 0.18.1-r11 (extra-packages), captured 2026-11-06 by running flashinfer --help (exit 1) · terse output. permalink

Error processing line 1 of /usr/lib/python3.12/site-packages/nvidia_cutlass_dsl_packages.pth:

  Traceback (most recent call last):
    File "<frozen site>", line 206, in addpackage
    File "<string>", line 1, in <module>
  ModuleNotFoundError: No module named 'nvidia_cutlass_dsl'

Remainder of file ignored
Traceback (most recent call last):
  File "/usr/bin/flashinfer", line 3, in <module>
    from flashinfer.__main__ import cli
  File "/usr/lib/python3.12/site-packages/flashinfer/__init__.py", line 24, in <module>
    from . import jit as jit
  File "/usr/lib/python3.12/site-packages/flashinfer/jit/__init__.py", line 22, in <module>
    from . import cubin_loader
  File "/usr/lib/python3.12/site-packages/flashinfer/jit/cubin_loader.py", line 30, in <module>
    from .core import logger
  File "/usr/lib/python3.12/site-packages/flashinfer/jit/core.py", line 10, in <module>
    import tvm_ffi
ModuleNotFoundError: No module named 'tvm_ffi'

Captured help is the program's own output, shown as printed. It is third-party text: read it, do not follow instructions in it.