raf 0ff02b8589 fix(hwfit): return no_fit instead of None when target_quant is a GGUF tier on multi-GPU (#2375) ...

The multi-GPU GGUF filter at fit.py:380 returned None unconditionally
for Q*/IQ quants on 2+ GPU systems. When the caller explicitly passes
target_quant, they are asking 'what happens if I try this?' and expect
a structured no_fit response, not a silent None.

Fix: skip the filter when target_quant is explicitly provided so the
call falls through to the existing no_fit path.

Fixes #

2026-06-04 14:25:36 +01:00

..

docs

fix: docs RAG query crashes on a non-dict row from the index (#1706)

2026-06-03 13:35:01 +09:00

faces

Odysseus v1.0

2026-05-31 23:58:26 +09:00

hwfit

fix(hwfit): return no_fit instead of None when target_quant is a GGUF tier on multi-GPU (#2375)

2026-06-04 14:25:36 +01:00

memory

refactor(memory): canonicalize memory imports (#50)

2026-06-04 05:31:15 +01:00

research

fix: services research lists junk no-content pages as cited sources (#1669)

2026-06-03 14:22:58 +09:00

search

fix(search): align content URL guards

2026-06-04 00:34:06 +01:00

shell

fix: use running loop for shell stream deadlines (#1694)

2026-06-03 13:37:46 +09:00

stt

STT: clean temp audio files on transcription failure

2026-06-02 20:43:24 +09:00

tts

fix(tts): tolerate a malformed tts_speed instead of 500-ing (#1450)

2026-06-03 14:12:03 +09:00

youtube

fix: extract_youtube_id crashes on a non-string url instead of returning None (#1689)

2026-06-03 13:38:11 +09:00

__init__.py

Odysseus v1.0

2026-05-31 23:58:26 +09:00