jpmschweitzer/odysseus
1
0
Fork 0
mirror of https://github.com/pewdiepie-archdaemon/odysseus.git synced 2026-09-30 03:52:21 +02:00
Code Issues Packages Projects Releases Wiki Activity
1,659 Commits 19 Branches 0 Tags
edd5ea36adad0f283e93c3bb2e84920094de379c
Commit Graph
3 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Zen0-99 2a422c00ec feat(model-picker): add remove-from-recent button to Recent section rows (#2894) 
* feat(model-picker): add remove-from-recent button to Recent section rows

* fix(model-picker): restore original browse-mode section logic, keep remove button only
 2026-06-07 17:45:59 +02:00
Zen0-99 bec594904d Fix/windows llama cpp serve and test upstream (#2669) 
* fix: code runner base64, Windows serve paths, endpoint cache clear, copy-log guards, model-picker remove-recent

* Revert model-picker 'remove from recent' feature and remove stray PR_DRAFT.md
 2026-06-05 14:53:33 +02:00
Zen0-99 7188737294 fix(hwfit): filter non-GGUF models on Windows (#2530) 
Odysseus only supports llama.cpp on Windows (vLLM/SGLang are
explicitly blocked). llama.cpp requires GGUF, so AWQ/GPTQ/FP8
safetensors models without a GGUF alternate should not be
recommended in the Cookbook on Windows hosts.

Changes:
- hardware.py: add 'platform': 'windows' to _detect_windows()
  so downstream logic can identify Windows hosts.
- fit.py: include is_windows in the existing GGUF-only filter
  alongside apple_silicon and consumer_amd.
- tests: add test_hwfit_windows.py with regression tests.

Fixes #122, #614 (root cause: unservable models recommended).
 2026-06-04 20:02:13 +02:00