lekt8 0e6cbd8315 Drop GPU-only flags from the CPU-only (-ngl 0) serve command (#1433) ...

A CPU-only llama.cpp serve config still emitted --flash-attn on and exported
GGML_CUDA_ENABLE_UNIFIED_MEMORY=1 (independent toggles, often left on by an Auto
profile), so the command mixed "zero GPU layers" with CUDA/flash-attn and failed
to start (issue #1291). Gate both on a _cpuOnly check (ngl == 0). GPU serving is
unchanged — the gate only affects the ngl=0 path.

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-03 04:26:15 +09:00

..

fonts

Odysseus v1.0

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

js

Drop GPU-only flags from the CPU-only (-ngl 0) serve command (#1433)

2026-06-03 04:26:15 +09:00

lib

Odysseus v1.0

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

app.js

Fix stale deleted sessions in sidebar (#1203)

2026-06-02 23:52:22 +09:00

index.html

Models: add Z.AI coding endpoint and GLM vision detection

2026-06-02 20:59:17 +09:00

landing.html

feat: Add mobile hamburger navigation menu and toggle functionality

2026-06-01 15:57:01 +04:00

login.html

Improve accessibility across core flows (#86)

2026-06-01 22:04:00 +02:00

manifest.json

Odysseus v1.0

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

style.css

Fix Edge/Chromium sidebar section-title clipping (#1420)

2026-06-03 04:24:29 +09:00

sw.js

Odysseus v1.0

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