Mikhail ChusavitinandClaude Sonnet 5 4ac9863353 fix(webui): keep ramp-up burns as a single multi-GPU task ...

buildNvidiaTaskSet only treated ParallelGPUs as a reason to keep all
selected GPUs in one task, so ramp-up (StaggerGPUStart) fell through
to per-model task splitting. When that split left a single GPU in a
task, resolveNvidiaRampPlan silently returned StaggerSeconds=0,
making the ramp-up toggle a no-op.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

2026-08-17 10:59:49 +03:00

..

app

fix(collector): surface PCIe link-speed degradation in component-status DB, sample it under load

2026-08-06 13:51:14 +03:00

collector

fix(nvidia): surface Xid 79/154 GPU bus-fall-off as a physical-reboot-required signal

2026-08-06 12:28:34 +03:00

platform

fix(nvidia): surface Xid 79/154 GPU bus-fall-off as a physical-reboot-required signal

2026-08-06 12:28:34 +03:00

runtimeenv

Refactor bee CLI and LiveCD integration

2026-03-13 16:52:16 +03:00

schema

gpu: collect reset-required/row-remap status and classify Xid codes by severity

2026-07-07 19:28:59 +03:00

updater

feat(audit): 1.1 — project scaffold, schema types, collector stub, updater trust

2026-03-05 10:32:12 +03:00

webui

fix(webui): keep ramp-up burns as a single multi-GPU task

2026-08-17 10:59:49 +03:00