mirror of
https://github.com/mudler/LocalAI
synced 2026-05-24 09:28:23 +00:00
69 lines
3 KiB
TOML
69 lines
3 KiB
TOML
|
# L4T arm64 (JetPack 7 / sbsa cu130) install spec for the sglang backend.
|
||
|
|
#
|
||
|
|
# Why this file exists, and why only the l4t13 BUILD_PROFILE consumes it:
|
||
|
|
#
|
||
|
|
# pypi.jetson-ai-lab.io hosts the L4T-specific torch / sglang / sgl-kernel
|
||
|
|
# wheels we need on aarch64 + cuda13, but it ALSO transparently proxies the
|
||
|
|
# rest of PyPI through `/+f/<sha>/<filename>` URLs that 503 frequently.
|
||
|
|
# With `--extra-index-url` + `--index-strategy=unsafe-best-match` (the
|
||
|
|
# historical fix in install.sh) uv would pick those proxy URLs for ordinary
|
||
|
|
# PyPI packages — markdown-it-py, anthropic, propcache, etc. — and trip on
|
||
|
|
# the 503s. See e.g. CI run 25439791228 (markdown-it-py-4.0.0).
|
||
|
|
#
|
||
|
|
# `explicit = true` on the index makes uv consult the L4T mirror ONLY for
|
||
|
|
# packages mapped under [tool.uv.sources]. Everything else goes to PyPI.
|
||
|
|
# This breaks the historical 503 path without losing access to the L4T
|
||
|
|
# wheels we actually need from there. Mirrors the equivalent fix already
|
||
|
|
# in backend/python/vllm/pyproject.toml.
|
||
|
|
#
|
||
|
|
# `uv pip install -r requirements.txt` does NOT honor [tool.uv.sources]
|
||
|
|
# (sources are project-mode only, not pip-compat mode), so install.sh's
|
||
|
|
# l4t13 branch invokes `uv pip install --requirement pyproject.toml`
|
||
|
|
# directly. Other BUILD_PROFILEs continue to use the requirements-*.txt
|
||
|
|
# pipeline through libbackend.sh's installRequirements and never read
|
||
|
|
# this file.
|
||
|
|
[project]
|
||
|
|
name = "localai-sglang-l4t13"
|
||
|
|
version = "0.0.0"
|
||
|
|
requires-python = ">=3.12,<3.13"
|
||
|
|
dependencies = [
|
||
|
|
# Mirror of requirements.txt — kept in sync manually for now since the
|
||
|
|
# l4t13 path bypasses installRequirements (see install.sh).
|
||
|
|
"grpcio==1.80.0",
|
||
|
|
"protobuf",
|
||
|
|
"certifi",
|
||
|
|
"setuptools",
|
||
|
|
"pillow",
|
||
|
|
# L4T-specific accelerator stack (sourced from jetson-ai-lab below).
|
||
|
|
"torch",
|
||
|
|
"torchvision",
|
||
|
|
"torchaudio",
|
||
|
|
# sglang on jetson — the [all] extra is deliberately omitted because it
|
||
|
|
# pulls outlines/decord, and decord has no aarch64 cp312 wheel anywhere
|
||
|
|
# (PyPI nor the jetson-ai-lab index ships only legacy cp35-cp37). With
|
||
|
|
# [all] uv backtracks through versions trying to satisfy decord and
|
||
|
|
# lands on sglang==0.1.16. The 0.5.0 floor matches the only major
|
||
|
|
# series the jetson-ai-lab sbsa/cu130 mirror currently publishes
|
||
|
|
# (sglang==0.5.1.post2 as of 2026-05-06). Bumping to >=0.5.11 here
|
||
|
|
# would make the build unsatisfiable until the mirror catches up.
|
||
|
|
# Gemma 4 / MTP recipes are therefore not supported on l4t13 — those
|
||
|
|
# features land on cublas12/cublas13 hosts that pull the newer wheel
|
||
|
|
# from PyPI. backend.py keeps backward compat with the 0.5.x SamplingParams
|
||
|
|
# field rename via runtime detection.
|
||
|
|
"sglang>=0.5.0",
|
||
|
|
# PyPI-resolvable packages that complete the runtime.
|
||
|
|
"accelerate",
|
||
|
|
"transformers",
|
||
|
|
]
|
||
|
|
|
||
|
|
[[tool.uv.index]]
|
||
|
|
name = "jetson-ai-lab"
|
||
|
|
url = "https://pypi.jetson-ai-lab.io/sbsa/cu130"
|
||
|
|
explicit = true
|
||
|
|
|
||
|
|
[tool.uv.sources]
|
||
|
|
torch = { index = "jetson-ai-lab" }
|
||
|
|
torchvision = { index = "jetson-ai-lab" }
|
||
|
|
torchaudio = { index = "jetson-ai-lab" }
|
||
|
|
sglang = { index = "jetson-ai-lab" }
|