 Alexander Korolev
|
fd30bf160a
web/report: settings button — per-agent client config for a recipe's served model
|
2 gün önce |
|
Alexander Korolev
|
8a683153dd
bench: add --node <name> — pin the bench target within a cluster (default: rank 0). A serve launched with 'serve --node' lives on a non-rank-0 node (solo Bolt on dgx3 inside 4nodes-switch), and benching the rank-0 head measured a different engine (the live kindling on dgx1 — model_not_available). pick_head tolerates the .lan suffix; web API passes node: None.
|
5 gün önce |
|
Alexander Korolev
|
0e826d4b35
bench: add --no-think and --timeout passthrough to tool-eval-bench — unblocks valid quality benches for thinking-by-default models (Ling, GLM-4.5-style) whose default reasoning blows the 120s/turn timeout and excludes most scenarios (the 10-16 fp8 Ling run scored 67/100 at 3.1% completion for exactly this reason)
|
6 gün önce |
|
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
|
1 hafta önce |
|
Alexander Korolev
|
f4aee53e0c
single working set: recipes/ + docker-images/ move to the shared repo checkout (../recipes) — dev config points at it via recipe_sources/docker_image_sources; validate gates over every configured source; web hosts the recipe-repo resync loop (--repo-sync-interval, default 10, 0 disables); playwright UI suites run serially (browser lock + split test legs)
|
1 hafta önce |
|
Alexander Korolev
|
f93a151d40
bench: --no-depth flag — skip the 16K..256K depth suite (quick-grasp campaigns: scenarios + typical-depth perf only)
|
1 hafta önce |
|
Alexander Korolev
|
b70649a547
feat(bench): --ssh-host — run tool-eval-bench on a remote host over SSH
|
2 hafta önce |
|
Alexander Korolev
|
bfbbf854b3
bench: the script-pty wrapper is macOS-only — util-linux script (Linux nodes) has no positional command and parsed the harness flags as its own ('unrecognized option --base-url'); non-macOS goes to the direct-exec fallback
|
3 hafta önce |
|
Alexander Korolev
|
d5a2032562
bench: warm-prefix depth measurement (--benchy-args=--enable-prefix-caching) — the c2 long-context 'collapse' (13.7/5.6/2.1) was llama-benchy's default cold-monolith branch, proven artifact (flag flips c2@65K 13.7 -> 52.1, TTFT 28.3s -> 1.5s); drop DEBUG from sparkring recipe (diagnosis closed)
|
3 hafta önce |
|
Alexander Korolev
|
0ee032e4e6
bench: depth-suite phase (16K/64K/128K/256K @ c2, 2 repeats) appended to the campaign log; report/tests.rs split (perf_box_tests) for the line cap
|
3 hafta önce |
|
Alexander Korolev
|
f39449c4ca
bench: --parallel passthrough + config C bench 166/184 (90/100, two-stream)
|
3 hafta önce |
|
Alexander Korolev
|
bc269457c2
bench(exl3-staged): 92/100 declarative-staging verification + bench --tokenizer passthrough
|
3 hafta önce |
|
Alexander Korolev
|
45462379ae
bench: re-attach the perf table the --json-file path drops; fix aiden recipe toml
|
3 hafta önce |
|
Alexander Korolev
|
c2e6c33d79
4x r39 perf: warm re-baseline via perf-only reruns (cold d0 c1 1772 -> 2018-2103), spec numbers corrected
|
1 ay önce |
|
Alexander Korolev
|
314812116c
feat: sm121 bench --perf-only (skip scenarios, re-baseline the perf table after a cold first row)
|
1 ay önce |
|
Alexander Korolev
|
1d73fd0945
serve/stop reliability + run ledger + archive curation
|
1 ay önce |
|
Alexander Korolev
|
081a0e6a0c
bench run package: per-run recipe copy + provenance manifest (recipe/config sha, launcher git sha, tool version, per-node image digest+build label); report shows provenance chip + Provenance column with drift flag
|
1 ay önce |
|
Alexander Korolev
|
9bf6e76e6c
adopt r35 (latest lab rev): full 3-fork pin profile + r35 4x-dcp4 recipe; image built on dgx5 (71m, checksum 8bb87348), boot gates green
|
1 ay önce |
|
Alexander Korolev
|
d46cc512c7
report: strip ANSI from served logs; bench logs saved clean
|
1 ay önce |
|
Alexander Korolev
|
87ad741ec8
bench: run tool-eval-bench under a pty (script -q) — rich Live deadlocked on plain stdout pipes after the perf phase (2x lane, 3/3 repro; 4x got lucky)
|
1 ay önce |
|
Alexander Korolev
|
52e1dc891d
bench: fix pump reading into empty buffer (EOF→EPIPE→silent exit 120)
|
1 ay önce |
|
Alexander Korolev
|
1ef3eebed6
bench: add sm121 bench — tool-eval-bench with auto-landed reports; move stop handler to docker/stop
|
1 ay önce |
