unsloth/.github
Daniel Han 1b7106162a ci(inference): port main's --local-dir gguf-cache pattern to tool-calling jobs
The Tool calling Tests jobs were the worst offender for HF_HOME cache
inflation. Same Qwen3.5-2B-UD-Q4_K_XL.gguf that's 1.28 GiB on disk
was landing as ~4.7 GiB in the actions/cache archive across all three
OS jobs:

  Linux Qwen IQ3_XXS  889 MB GGUF -> 4313 MB cache (4.85x)
  Mac   Qwen Q4_K_XL 1278 MB GGUF -> 4692 MB cache (3.7x)
  Win   Qwen Q4_K_XL 1278 MB GGUF -> 4692 MB cache (3.7x, 211 s upload)

The 3-5x inflation comes from caching the entire HF_HOME tree:
xet chunks + blobs + snapshots are all stored, plus on Windows
snapshot symlinks materialise as full copies (NTFS symlinks need
admin). main branch has long since moved to a leaner pattern --
hf download with --local-dir gguf-cache stores the flat .gguf only
and Studio's /api/inference/load takes an absolute file path.

Port main's pattern back to PR 5312's three tool-calling jobs:

  Cache step path:  hf-cache       -> gguf-cache
  Cache step key:   <os>-hf-<repo>-<variant>-v1
                 -> <os>-gguf-<repo>-<file>-v1
  Download:         hf download <repo> <file>
                 -> hf download <repo> <file> --local-dir gguf-cache
  Load:             model_path=<repo>, gguf_variant=<variant>
                 -> model_path=$GITHUB_WORKSPACE/gguf-cache/<file>

Cache size drops 4.7 GiB -> 1.28 GiB; Post Cache step time drops
from 211 s -> ~60 s on first runs, and the steady-state cache-hit
restore is also faster (smaller archive).

Windows path handling: GITHUB_WORKSPACE on windows-latest is a
backslash path ("D:\a\unsloth\unsloth"), which would explode JSON
escaping if embedded directly. Use bash parameter expansion to
flip backslashes to forward slashes; pathlib.Path on Windows accepts
forward slashes natively, so Studio's loader sees a normal path.

Trade-off: the tool-calling jobs no longer exercise Studio's
gguf_variant resolution path. The OpenAI/Anth and JSON+images jobs
still cover that path on every PR push, so coverage of the variant-
to-file mapping is retained at the workflow level.

The OpenAI/Anth and JSON+images jobs intentionally stay on HF_HOME --
their GGUFs are smaller (gemma-3-270m at ~250 MB, gemma-4-E2B at
~2.4 GB + mmproj). The post-step upload cost for those is dominated
by their actual file size, not the inflation factor; switching them
adds churn without proportional savings.
2026-05-08 09:10:57 +00:00
..
ISSUE_TEMPLATE Update issue template 2026-03-23 10:10:15 +05:30
workflows ci(inference): port main's --local-dir gguf-cache pattern to tool-calling jobs 2026-05-08 09:10:57 +00:00
CODEOWNERS Update CODEOWNERS 2026-03-13 13:38:19 -07:00
dependabot.yml CI(security): defense-in-depth additions across 7 axes 2026-05-07 00:09:40 +00:00
FUNDING.yml Update FUNDING.yml (#3792) 2025-12-28 19:57:43 -08:00