yy-fighting
|
b3ead2cb77
|
untrack tp*_dp* outputs again; fix gitignore pattern (add platform/experiment level)
|
2026-07-17 07:13:48 +00:00 |
|
yy-fighting
|
3b1539d446
|
fix over-corrected scripts/common paths (4 levels -> 3) in 12 scripts
|
2026-07-17 07:09:40 +00:00 |
|
yy-fighting
|
b01640aa20
|
commit only aggregated adaptive results; untrack tp*_dp* raw outputs and metrics
- keep adaptive_points/shapes/summary jsonl+md, run_manifest.json, shapes.tsv
- untrack tp*_dp*/ subdirs (raw_outputs, metrics, logs, gpu_logs) and ignore them in .gitignore
- update NEW_PLATFORM_GUIDE commit convention accordingly
|
2026-07-17 06:28:55 +00:00 |
|
yy-fighting
|
8652a685e6
|
rewrite README, add new platform onboarding guide, fix broken scripts/common paths
- rewrite README with project purpose, standard workflow, corrected index
- add docs/NEW_PLATFORM_GUIDE.md (new GPU onboarding SOP, GLM5.2 reuse)
- fix ../../scripts/common -> ../../../scripts/common in 42 experiment scripts
- refresh stale docs (EXPERIMENT_GUIDE, H200_QUICKSTART, ADAPTIVE_CONCURRENCY_USAGE, BENCHMARK_WORKFLOW)
- remove dead code (dp_proxy.py) and .bak leftovers
- add p800 adaptive results (tp4_dp2/tp8_dp1 metrics + summary)
- gitignore envs/charts and .tmp_charts
|
2026-07-17 06:18:05 +00:00 |
|
SSKJ Dev
|
90f0257ae0
|
update result
|
2026-07-17 02:19:22 +00:00 |
|
SSKJ Dev
|
0591c401ab
|
update stop method
|
2026-07-16 13:02:29 +00:00 |
|
SSKJ Dev
|
c2a3024a1b
|
update SEARCH_INITIAL_BACKOFF_CONCURRENCIES
|
2026-07-16 08:58:31 +00:00 |
|
SSKJ Dev
|
20cb4e35c2
|
update
|
2026-07-16 06:25:00 +00:00 |
|
SSKJ Dev
|
dcb8cd2131
|
feat(adaptive): add TTFT SLO early-stop and fix relative paths for h20 experiments
- Add TTFT_SLO_MS and ENABLE_TTFT_SLO_STOP config to adaptive search
- Stop searching current shape when TTFT P95 exceeds SLO (default 3000ms)
- Fix relative paths in h20 scripts: ../../scripts/common -> ../../../scripts/common
- Update compare.py default TTFT limit to 4000ms
|
2026-07-16 05:15:51 +00:00 |
|
SSKJ Dev
|
a4e38b9e33
|
Reorganize experiments into hardware-specific subdirectories
Move all experiments under hardware-specific folders:
- experiments/h200/ : H200 GPU experiments (15 dirs)
- experiments/h20/ : H20 GPU experiments (2 dirs)
- experiments/p800/ : Kunlun P800 experiments (3 dirs)
- experiments/pro6000/ : RTX 6000D experiments (2 dirs)
This improves discoverability and keeps hardware-specific configs
isolated from each other.
|
2026-07-16 04:11:07 +00:00 |
|