jammi-server-cu12
GPU build of the Jammi engine server, packaged as a pip-installable wheel that
ships the CUDA-enabled jammi-server binary behind a jammi-server console
script.
pip install jammi-server-cu12
jammi-server --help
The CUDA runtime libraries (libcudart, libcublas, libcublasLt,
libcurand, libnvrtc) are pulled in as nvidia-*-cu12 wheel dependencies; the
console script prepends their lib/ directories to LD_LIBRARY_PATH before
exec'ing the binary, so no system CUDA install is required (only an NVIDIA driver
on the host). This package and jammi-server (CPU) both provide the
jammi-server command — install exactly one.
Requirements
- NVIDIA GPU of compute capability 8.0 or newer (Ampere A100, A10/A6000,
Ada L4/L40S, Hopper H100). The kernels are built at
compute_80and the driver JIT-forwards them to 8.6 / 8.9 / 9.0. Turing (7.5, e.g. Tesla T4) is not supported by this build. - NVIDIA driver r560 or newer (Linux: ≥
560.28.03). The kernels ship as PTX compiled with the CUDA 12.6 toolkit, which the deployment driver JIT-compiles at model load; a driver below the CUDA 12.6 line (for example550.x, which tops out at CUDA 12.4) cannot compile that PTX and the server exits at startup with a clear driver-too-old error rather than a rawCUDA_ERROR_UNSUPPORTED_PTX_VERSIONat first inference.nvidia-smishows the installed driver and its max CUDA version.
1 maintainer
Metadata
1 maintainer
Release files for jammi-server-cu12 0.48.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| jammi_server_cu12-0.48.0-py3-none-manylinux_2_28_x86_64.whl | Python 3 | none | Linux glibc 2.28+ x86-64 | Details |
Release files / jammi_server_cu12-0.48.0-py3-none-manylinux_2_28_x86_64.whl
| Download URL | jammi_server_cu12-0.48.0-py3-none-manylinux_2_28_x86_64.whl |
|---|---|
| Size | 70.7 MB |
| Tags | Linux glibc 2.28+ x86-64 Python 3 |
|
SHA-256 checksum How to use checksums |
e980b0c2960c736c36ca602ad9fd206aa7ffe74b276a865173d7199b213ea928
|
|
BLAKE2b-256 checksum How to use checksums |
ddc6bd4942cb09277707ac2cc10ed5d28656a546bb6b86a70a135e30fb445b33
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.15
|
