 Alexander Korolev
|
f4b4f62683
upstream-watch 10-16: Ling fp4 research — ling3 parser, fp8-as-source (Ling is mixed bf16+fp8 ckpt), fp4 format spec (mxfp4 experts+fp8 dense), single-Spark serving via cookbook, fp8->mxfp4 converter path + reference files, Qwen4-27B warm-up plan
|
hace 1 semana |
|
Alexander Korolev
|
909162aef1
upstream-watch + shift log 10-16: live model probes — Ling fp8 feasible on GB10, Step-5 SM121 DSA blocker; entrypoint=[vllm,serve] gap noted
|
hace 1 semana |
|
Alexander Korolev
|
621d14da70
night shift 2026-10-16 log: DGPP provisioning e2e (4 bugs fixed), Ling/Step-5 feasibility + prep recipes, repo/forum mining, cluster powered off
|
hace 1 semana |
|
Alexander Korolev
|
5178315eb0
upstream-watch 10-16: DGPP forum mining — HEAD release notes add dense Qwen3.8-27B + GLM-5.3 quant + DGPP_NO_SWAP (pin-bump candidate); community 2x RoCE single-lane GID3
|
hace 1 semana |
|
Alexander Korolev
|
accf2728ae
upstream-watch 2026-10-16: Ling BailingMoeV3 supported on v0.31.0 (no nightly) but NVFP4 cut empty; Step-5 is step5_vl VL needing dedicated image; dgpp HEAD moved; v0.32.0 still rc; DGPP w2 deploy prereqs
|
hace 1 semana |
|
Alexander Korolev
|
28f909758a
engine-drivers spec: correct DGPP provisioning model (rank0-only install, idempotent, space-nodes, script-file tee) + DGPP deploy prereqs from live w2 run
|
hace 1 semana |
|
Alexander Korolev
|
89013fbb75
native/dgpp: fix provisioning from the first live DGPP w2 run
|
hace 1 semana |
|
Alexander Korolev
|
7e0fefcbb2
night-shift plan 2026-10-16: DGPP w2 finish, Ling-3.1-flash + Step-5-Preview tests, forum/repo mining, end-of-shift 8x power-off
|
hace 1 semana |
|
Alexander Korolev
|
1d6fbf9da2
native/dgpp: on-demand DGPP provisioning (clone-at-pin + release.sh + install + rev-marker)
|
hace 1 semana |
|
Alexander Korolev
|
503fe88e78
web/report: recipe logs open a dashboard WINDOW, not an inline stream
|
hace 1 semana |
|
Alexander Korolev
|
5194805e77
native/dgpp: emit paths.resident_cache in cluster JSON; exempt Native deploy from multi-node-tp1
|
hace 1 semana |
|
Alexander Korolev
|
06a4103738
shift log: first-class gr8 + DGPP engine drivers (Phases 1-3)
|
hace 1 semana |
|
Alexander Korolev
|
fe1d70ada3
engine: DGPP driver + native deploy (Phase 3) — head-coordinated, generated cluster JSON/.env
|
hace 1 semana |
|
Alexander Korolev
|
f772f3d5e6
engine: gr8 driver (Phase 2) — --tp/--peers rendezvous, --model, fixed API port
|
hace 1 semana |
|
Alexander Korolev
|
5be604ccfe
engine: EngineDriver trait — first-class engine abstraction (Phase 1)
|
hace 1 semana |
|
Alexander Korolev
|
28af1b0d4d
upstream-watch 10-15: MiMo 4x rebase done (90/100, +19% decode)
|
hace 1 semana |
|
Alexander Korolev
|
f6e334a07b
shift log 2026-10-15: MiMo 4x rebase to SparkRing 2026.10.4 (dgx5 disk recovery, digest re-attach sync, 90/100 bench, +19% decode)
|
hace 1 semana |
|
Alexander Korolev
|
ef7298e1ee
upstream watch 10-15: v0.32.0rc2 imminent (flashinfer 0.7.1 + SM12x NVFP4 KV + DSpark scheduler fix), SparkRing 2026.10.4 validates the MiMo rebase image + adds TP2-DCP2, DGPP adds Qwen3.8-27B, Nemotron-3.5-Bolt 24GB single-Spark, Ling-3.1-flash 572B day-0 NVFP4, net-sircl DAC plugin, CRS812 fabric resolution
|
hace 1 semana |
|
Alexander Korolev
|
fd3acf21a7
shift log: add-on 1.1.12 — row controls in the expanded section (serve/stop, live logs, bench job)
|
hace 1 semana |
|
Alexander Korolev
|
606670fa28
recipes panel: move row controls into the expanded section (before the toml) — serve/stop, a live log tail (▤ logs, /api/logs attach + /events stream, node picker) for running recipes, and ⚡ bench (new POST /api/bench tracked job, standard seed-42 campaign, report lands in the recipe repo)
|
hace 1 semana |
|
Alexander Korolev
|
8e849667ac
shift log: add-on 1.1.11 built + deployed to the Pi (V1 /addons update path, HAOS 18.3 layout, fleet_up verified live)
|
hace 1 semana |
|
Alexander Korolev
|
f00b155eda
recipes panel: manual repo-sync button, per-row serve/stop actions, fleet-based running state (no-ledger machines), dock menu anchored to the + button
|
hace 1 semana |
|
Alexander Korolev
|
381475a96c
report viewer: follow-SSE under a mount prefix (META.base), no double-append on (re)baseline; regression test
|
hace 1 semana |
|
Alexander Korolev
|
9ef54874b6
AGENTS: bench flag semantics (optional label, opt-in depth)
|
hace 1 semana |
|
Alexander Korolev
|
425da04ac3
bench: --label optional (default 'perf' for perf-only), depth suite now opt-in (--depth), parse perf-box caveat asterisks, quiet json warning for perf-only
|
hace 1 semana |
|
Alexander Korolev
|
327945a562
removed dhat logs from repo
|
hace 1 semana |
|
Alexander Korolev
|
f914d20e60
removed dhat binary from repo
|
hace 1 semana |
|
Alexander Korolev
|
a70b998b5b
shift log 10-15: final state — 2x up on v0.31.0, smoke passed
|
hace 1 semana |
|
Alexander Korolev
|
358649ef84
shift log 10-15: full rebase saga + draft-trunc guard + serve state
|
hace 1 semana |
|
Alexander Korolev
|
f16c901fde
shift log 10-15: overlay-rebase root cause of the 9s crash
|
hace 1 semana |
