Repository navigation

feat(vllm): enhance OOM diagnostics and guidance in serve summary (eai-8059) - #284

Open

r0x0r wants to merge 88 commits into

mainfrom

eai-8059-oom-memory-knobs-note

Commits on Sep 8, 2026

feat(vllm): add GPU memory utilization hint for OOM errors and improve documentation
r0x0r
committed
abf6b4b
fix(vllm): validate --gpu against sysfs GPU count and harden DRM fallback
r0x0r
committed
38257fe
fix(vllm): validate --gpu against amd-smi-independent count; harden DRM guard
r0x0r
committed
af059ae
feat(diagnose): add the vLLM out-of-memory failure mode to the catalog (EAI-8060) (#290)
r0x0r
committed
956891f
fix(serve): validate --gpu against the usable-device set, not its length (EAI-8058)
r0x0r
committed
235adb9
docs(vllm): remove duplicate code-fence opener in OOM workaround example
r0x0r
committed
77f26cd
serve: address OOM diagnosis review — decouple engine hint from scorer, dedup keyword spans, anchor per-line
r0x0r
committed
e62ee2f
test(vllm): cover serve-plan low-VRAM OOM guidance on the GPU lane (EAI-8058)
r0x0r
committed
5702b55
feat(vllm): OOM detection, serve-summary memory guidance, and diagnose routing (EAI-8059)
r0x0r
committed
eb694a6
serve: address EAI-8059 re-review — validate --gpu before engine work, tighten OOM negative assertion
r0x0r
committed
7c09129
fix(vllm): reconcile OOM detector with diagnose threshold and de-dup env const (eai-8059)
r0x0r
committed
83ecfaa

Commits on Sep 9, 2026

Commits on Sep 10, 2026

Commits on Sep 11, 2026

Commits on Sep 14, 2026

Commits on Sep 15, 2026

Commits on Sep 17, 2026

Commits on Sep 18, 2026

Commits on Sep 22, 2026

Commits on Sep 23, 2026

Merge remote-tracking branch 'origin/main' into pr251-round4-doc-fix
r0x0r
committed
b6e0a50

Commits on Sep 24, 2026

Commits on Sep 25, 2026

Merge remote-tracking branch 'origin/gpu-out-of-memory' into wip-284-m3
r0x0r
committed
6c0d537

Commits on Sep 29, 2026

Commits on Sep 30, 2026

Commits on Oct 2, 2026

Commits on Oct 6, 2026