unsloth/studio
Daniel Han 2f3eae9846
Studio: resolve llama.cpp prebuilts via the release-assets CDN to avoid GitHub API rate limits (#7086)
* Studio: resolve llama.cpp prebuilts via the release-assets CDN to avoid GitHub API rate limits

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Studio: resolve manifest-named prebuilt assets on the download-host fast path

Add tag-pinned CDN URLs for any manifest artifact whose hash is keyed under an
upstream-tag alias in the checksum asset, so the fast path resolves the same
assets the API path does. Cover the resolve body directly (only download_bytes
stubbed) and soften the doc's validation-equivalence wording.

* Studio: pin llama.cpp fast path to the releases/latest redirect tag

Derive the authoritative latest tag from GitHub's /releases/latest redirect
target instead of trusting the checksum asset's self-reported release_tag, so the
existing release_tag cross-check in parse_approved_release_checksums is a real
check again: a stale or mis-tagged checksum asset now falls back to the API. Pin
every fast-path URL to that tag. Fall back to the API on a manifest 404 as well,
since an in-progress release can publish the checksum asset before the manifest,
matching the sha256 404 handling. Document the releases/latest (created_at /
make_latest) versus published_at ordering divergence and why it is an accepted,
mitigated tradeoff.

* Studio: drop the llama.cpp prebuilt-resolution doc

Remove studio/docs/llama-cpp-prebuilt-resolution.md and the docstring pointer to
it; the resolution rationale (the created_at/make_latest vs published_at ordering
nuance) stays inline in _download_host_latest_release_tag.

* Studio: tighten llama.cpp download-host fast-path comments

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2026-07-14 03:30:17 -07:00
..
backend Studio: persistent stdio MCP sessions so server state survives across tool calls (#7080) 2026-07-14 02:28:43 -07:00
frontend Studio: persistent stdio MCP sessions so server state survives across tool calls (#7080) 2026-07-14 02:28:43 -07:00
src-tauri Speed up Studio startup path (#6899) 2026-07-07 18:08:07 -07:00
__init__.py Final cleanup 2026-03-12 18:28:04 +00:00
install_llama_prebuilt.py Studio: resolve llama.cpp prebuilts via the release-assets CDN to avoid GitHub API rate limits (#7086) 2026-07-14 03:30:17 -07:00
install_node_prebuilt.py Pin isolated Node.js installer to committed sha256 digests (#6625) 2026-06-24 05:47:58 -07:00
install_python_stack.py Studio: fix flash-attn and torchao install on Blackwell (sm_100+) GPUs (Closes #6961) (#6970) 2026-07-08 06:38:10 -07:00
LICENSE.AGPL-3.0 Add AGPL-3.0 license to studio folder 2026-03-09 19:36:25 +00:00
node_prebuilt_pins.json Pin isolated Node.js installer to committed sha256 digests (#6625) 2026-06-24 05:47:58 -07:00
package-lock.json ci: advisory lockfile supply-chain audit (no install-script changes) (#5604) 2026-05-19 05:56:56 -07:00
package.json ci: advisory lockfile supply-chain audit (no install-script changes) (#5604) 2026-05-19 05:56:56 -07:00
setup.bat Final cleanup 2026-03-12 18:28:04 +00:00
setup.ps1 Tighten Studio instruction-file cleanup boundaries (#7097) 2026-07-13 01:46:23 -07:00
setup.sh Tighten Studio instruction-file cleanup boundaries (#7097) 2026-07-13 01:46:23 -07:00
Unsloth_Studio_Colab.ipynb Studio Colab: opt-in shareable Cloudflare tunnel link (#6684) 2026-06-26 00:56:23 -07:00