Disable pip cache for Cookbook dependency installs (off the home disk) (#1477)

Cookbook dependency installs (vLLM and friends) build large wheels; pip's
default cache lives under $HOME/.cache/pip, so on a small home filesystem the
build dies mid-way with "[Errno 28] No space left on device" (issue #1219) and
the dependency ends up "installed" but unusable (issue #1459).

Add `--no-cache-dir` to the dependency pip-install command (the maintainer's
suggested PIP_CACHE_DIR= workaround, made the default) via a small
_pip_install_no_cache() helper applied at the install chokepoint. Consistent
with the existing --no-cache-dir on the llama-cpp-python build. Idempotent;
non-pip-install serve commands are untouched.

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
lekt8
2026-06-03 13:23:49 +08:00
committed by GitHub
parent 1feb2ae7d5
commit ffb8fd16bc
3 changed files with 40 additions and 1 deletions

View File

@@ -148,6 +148,21 @@ def _local_tooling_path_export(executable: str) -> str:
return f'export PATH="{esc}:$PATH"'
def _pip_install_no_cache(cmd: str) -> str:
"""Add ``--no-cache-dir`` to a pip install command.
Cookbook dependency installs (vLLM, llama-cpp-python, …) build large wheels;
pip's default cache lives under ``$HOME/.cache/pip`` and these builds can fill
a small home filesystem with ``[Errno 28] No space left on device`` mid-build
(issue #1219), leaving the dependency "installed" but unusable (#1459).
Disabling the cache for these one-off installs keeps them off the home disk
(the maintainer's suggested ``PIP_CACHE_DIR=`` workaround, made the default).
Idempotent; leaves non-pip-install commands untouched."""
if not cmd or "pip install" not in cmd or "--no-cache-dir" in cmd:
return cmd
return cmd.replace("pip install", "pip install --no-cache-dir", 1)
def _pip_install_attempt(pip_cmd: str) -> str:
"""Wrap a single pip install command so its exit status survives the
fallback chain and its stderr is visible in the tmux log on failure.

View File

@@ -38,7 +38,7 @@ from routes.cookbook_helpers import (
_ps_squote, _bash_squote, _validate_serve_cmd, _parse_serve_phase,
_safe_env_prefix, _local_tooling_path_export, _append_serve_preflight_exit_lines,
_append_serve_exit_code_lines, _append_llama_cpp_linux_accel_build_lines, _cached_model_scan_script,
_ollama_bind_from_cmd, _pip_install_fallback_chain, _venv_safe_local_pip_install_cmd,
_ollama_bind_from_cmd, _pip_install_fallback_chain, _pip_install_no_cache, _venv_safe_local_pip_install_cmd,
ModelDownloadRequest, ServeRequest,
)
@@ -841,6 +841,10 @@ def setup_cookbook_routes() -> APIRouter:
)
is_pip_install = bool(req.cmd and "pip install" in req.cmd)
if is_pip_install:
# Keep big dependency wheel builds (vLLM, …) off the home filesystem's
# pip cache so they don't fail mid-build with "No space left" (#1219)
# and leave the dep installed-but-unusable (#1459).
req.cmd = _pip_install_no_cache(req.cmd)
# PEP-508-style package spec — letters, digits, `.-_` for the
# name; `[` `]` for extras; `<>=!~,` for version specifiers.
# v2 review HIGH-14: tightened from the previous regex which

View File

@@ -415,3 +415,23 @@ def test_cached_model_scan_reports_plain_dir_gguf(tmp_path):
assert ggufs[1]["size_bytes"] == len(b"part1part2part3")
assert ggufs[2]["quant"] == "Q6_K_XL"
assert ggufs[3]["quant"] == "BF16"
# ── #1219 / #1459: keep big dependency wheel builds off the home pip cache ──
def test_pip_install_no_cache_injects_flag():
from routes.cookbook_helpers import _pip_install_no_cache
assert _pip_install_no_cache("python -m pip install vllm") == \
"python -m pip install --no-cache-dir vllm"
assert _pip_install_no_cache("pip install -q huggingface-hub") == \
"pip install --no-cache-dir -q huggingface-hub"
def test_pip_install_no_cache_is_idempotent_and_scoped():
from routes.cookbook_helpers import _pip_install_no_cache
# already present -> unchanged
already = "pip install --no-cache-dir vllm"
assert _pip_install_no_cache(already) == already
# not a pip install -> unchanged
assert _pip_install_no_cache("vllm serve --model x") == "vllm serve --model x"
assert _pip_install_no_cache("") == ""