27d1c8fa92
Add L-C-A workload profile metric and CLI profile commands
...
Implement the paper's 10-dimensional L-C-A workload feature vector
(RobustScaler-normalized, sim=exp(-||dz||)) in lca.py, and wire it into
`aituner profile window` / `aituner profile similarity`. Covered by tests.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com >
2026-06-15 14:02:24 +08:00
d0c89dac48
Clean marked trial engine processes
2026-05-16 15:51:04 +08:00
cf9b8b3f68
Clean vLLM process groups after parent exit
2026-05-16 14:52:05 +08:00
5a879a8592
Fix decode harness partial probe handling
2026-05-16 14:18:07 +08:00
5c2958e6c1
Constrain harness topology by visible GPUs
2026-05-13 01:25:31 +08:00
e3ed775afd
Fix harness SLO early-stop diagnosis
2026-05-12 22:20:01 +08:00
17e9681ca0
Add profile-driven harness planner
2026-05-12 21:28:44 +08:00
2d03b1cd4c
Add SLO-driven topology frontier harness guard
2026-05-12 21:00:49 +08:00
e1125475ae
Minimize no-harness ablation prompt
2026-05-12 09:42:53 +08:00
ae756600ce
Support full-range and incumbent-floor search modes
2026-05-11 12:58:46 +08:00
8516cd88c0
Use full search range for every trial
2026-05-11 12:50:22 +08:00
14259fcec9
Measure lower-range performance for infeasible trials
2026-05-10 14:30:34 +08:00
bdb08f6edc
Handle missing streamed token metrics
2026-05-10 02:40:00 +08:00
adc4351e5d
Report latency stats for infeasible baseline
2026-05-08 11:10:34 +08:00
f212673f44
Stop tuning when baseline is infeasible
2026-05-08 01:07:36 +08:00
a7a5e9ad80
Make tune trial budget resumable
2026-05-07 17:18:06 +08:00
c1ff64381d
Harden trial measurement accounting
2026-05-06 21:18:09 +08:00
f653af09a8
Stop harness when feasible probe reaches search high
2026-05-06 17:59:09 +08:00
5d96689ea6
Make harness runtime refinement memory safe
2026-05-06 17:37:31 +08:00
0622e23817
Guide harness runtime refinement after TP
2026-05-06 02:46:07 +08:00
50067c926d
Add harness guided first topology probe
2026-05-06 02:28:46 +08:00
4c066c4e4e
Stop harness when search high is saturated
2026-05-02 11:04:59 +08:00
4ef69cce78
Make harness stop conservative for ablation
2026-05-02 09:47:16 +08:00
1a3d628268
Add harness early stop ablation
2026-05-02 08:08:14 +08:00
6d3459c82d
Document decode harness one-shot mechanism
2026-05-02 06:25:06 +08:00
9e5394b557
Inherit incumbent topology for runtime validation
2026-04-30 09:33:49 +08:00
f59919e21c
Clarify base-relative validation patches
2026-04-30 06:52:09 +08:00
38ff4380e5
Make strong incumbent trigger validation phase
2026-04-28 20:54:05 +08:00
c9089cf4f0
Ignore non-SLO probe bookkeeping in bottleneck diagnosis
2026-04-28 06:58:38 +08:00
a9943e0240
Use probe sequence bottlenecks in harness
2026-04-28 06:57:45 +08:00
39aa47fbf1
Add generic decode-only harness guidance
2026-04-28 06:46:18 +08:00
29d0548e06
Stop after strong incumbent harness gains
2026-04-26 01:29:05 +08:00
6bac389aae
Add infeasible plateau guard to harness
2026-04-25 18:49:23 +08:00
6c04b9dbbc
Evaluate baseline before LLM tuning
2026-04-25 17:14:05 +08:00
2d7ebe50ee
Drain inflight requests after early stop
2026-04-25 16:57:01 +08:00
2dc2815620
Make harness verification portable
2026-04-25 16:37:13 +08:00
2c5e9af02a
Add harness-guided tuning prompts
2026-04-25 16:35:33 +08:00
4625fba487
trace: make window materialization atomic
2026-04-12 23:09:30 +08:00
631a076498
trace: include weekend legacy windows
2026-04-12 22:43:02 +08:00
3f20ddf87e
Add qwen235b prefill-only tuning support
2026-04-11 21:00:02 +08:00
5e54e9c8f5
Add multi-window baseline vs tuned compare flow
2026-04-11 13:51:54 +08:00
83325b2f76
Reset new topology groups to full binary search
2026-04-11 00:36:45 +08:00
a4d54442db
Fix topology-aware incumbents for qwen27b tuning
2026-04-11 00:32:41 +08:00
8d0777e5e2
Add topology-aware qwen27b 0-8k tuning
2026-04-10 17:41:54 +08:00
9422d43737
Prioritize topology exploration in decode tuning
2026-04-10 10:25:41 +08:00
d582a8ed1b
Validate served model name consistency
2026-04-09 22:50:23 +08:00
ef78fe7eb5
Add topology-aware tuning constraints
2026-04-09 21:07:51 +08:00
7371d6635c
Force codex stream to use chat completions
2026-04-09 14:49:40 +08:00
ceafecd8f0
Fix list flag serialization for engine launch
2026-04-09 11:52:27 +08:00
c158807fac
Add decode-only study mode support
2026-04-09 11:23:17 +08:00
