Commit Graph

398 Commits

Author SHA1 Message Date
a21382c8aa Raise Q235 profiler token limit 2026-07-19 05:45:37 +08:00
5067bc2cb1 Expose nvcc to Q235 FlashInfer profiling 2026-07-19 05:42:26 +08:00
39e4719b28 Run Qwen235 profilers from Frontier source 2026-07-19 03:00:04 +08:00
79e9870975 Defer Qwen235 campaign until Qwen30 completion 2026-07-19 02:54:32 +08:00
80a067e3a5 Orchestrate Qwen235 four-case fidelity campaign 2026-07-19 02:52:54 +08:00
3e32ea609f Cover Qwen235 MNS128 graph buckets 2026-07-19 02:48:51 +08:00
40bac6dbf4 Add Qwen235 same-stack Frontier profiling campaign 2026-07-19 02:46:58 +08:00
e631f6a269 Add Qwen235 Frontier latency surface runner 2026-07-19 02:44:55 +08:00
a3c8cb5808 Add Qwen235 Frontier MoE portability smoke 2026-07-19 02:42:28 +08:00
f4813cf537 Add Qwen235 vLLM 0.20 real surface runner 2026-07-19 02:39:16 +08:00
c8383c9c4c Launch Qwen30 fixed pressure comparison 2026-07-19 02:25:15 +08:00
7ea9635878 Record fixed PD pressure calibration result 2026-07-19 01:45:17 +08:00
33b73afe9b Narrow fixed PD pressure sweep around load knee 2026-07-19 01:26:09 +08:00
909a80f0a6 Reuse validated FlashInfer cache for pressure probe 2026-07-19 01:13:50 +08:00
9837fa5133 Match Qwen30 probe file descriptor limit 2026-07-19 01:07:57 +08:00
6726318792 Profile fixed PD workload pressure against trace anchor 2026-07-19 00:54:48 +08:00
e98608911e Resume valid Qwen30 latency cells safely 2026-07-18 17:27:12 +08:00
f11daa6776 Fix Qwen30 exact trace served-model routing 2026-07-18 11:56:43 +08:00
b9523cef5c Pin DeepGEMM nvcc for Qwen235 smoke 2026-07-18 11:15:22 +08:00
b7f9cef9c5 Keep Qwen30 JIT cache scoped to experiment 2026-07-18 11:11:10 +08:00
ecb45cf762 Extend Qwen30 JIT readiness for latency surface 2026-07-18 11:09:22 +08:00
686b050517 Isolate Qwen235 DeepGEMM JIT cache 2026-07-18 10:57:48 +08:00
28ffb22bee Create Qwen30 case output before launch logging 2026-07-18 10:50:11 +08:00
a01c1206ab Launch frozen Qwen30 latency case surfaces 2026-07-18 10:48:45 +08:00
5fc0b48fa1 Extend Qwen235 smoke readiness deadline 2026-07-18 10:32:21 +08:00
7a437b4d91 Allow fixed runtime preflight resume 2026-07-18 01:11:37 +08:00
12705411f9 Record Qwen235 portability experiment gate 2026-07-18 01:08:54 +08:00
ddacc5f7a6 Add Qwen235 vLLM 0.20 compatibility gate 2026-07-18 01:08:08 +08:00
a7e3c0fdf3 Record fixed-case vLLM runtime state 2026-07-18 01:05:46 +08:00
44104bd96e Prepare remaining Qwen30 latency cases 2026-07-18 01:03:06 +08:00
65fee8450a Record graph-aligned Frontier result 2026-07-18 00:30:59 +08:00
e6f3e4a690 Audit graph-aligned Frontier surface 2026-07-18 00:09:06 +08:00
e2cd43808d Bound graph predictor grid to runtime 2026-07-17 23:41:01 +08:00
27a2a3468a Use verified FlashInfer profile cache 2026-07-17 23:27:07 +08:00
2deb53cb72 Allow graph linear profile smoke 2026-07-17 23:25:15 +08:00
bdc357dc6c Align Frontier piecewise graph profiles 2026-07-17 23:22:42 +08:00
47355a9411 Record corrected Frontier liveness probe 2026-07-17 22:50:00 +08:00
d3be91dd58 Audit Frontier prefix-cache trace contract 2026-07-17 22:42:57 +08:00
e7b482658e Prepare cache-consistent T1 real smoke 2026-07-17 13:29:18 +08:00
8b054ffcb1 Bound Frontier predictor training parallelism 2026-07-17 13:02:08 +08:00
903cbe682d Record Frontier trace stalls without ranking them 2026-07-17 12:46:57 +08:00
03aa794448 Isolate FlashInfer cache for trace replay 2026-07-17 12:44:50 +08:00
2aa713f5d6 Prepare sealed exact-trace real smoke 2026-07-17 11:55:12 +08:00
e9ae04d852 Add exact production-trace real replay client 2026-07-17 10:40:36 +08:00
ec775cdafd Correct F1 to a steady fixed-QPS workload 2026-07-17 10:36:28 +08:00
10afe4e2e8 Freeze long-context Frontier profile 2026-07-17 10:30:37 +08:00
b6ef6eeae7 Add long-context attention profile closure 2026-07-17 10:26:21 +08:00
202ae718b3 Freeze batch-aware Frontier ablation 2026-07-17 10:22:56 +08:00
a2cf361ffe Generalize Qwen30 fixed-shape real runner 2026-07-17 10:17:21 +08:00
6e8704d525 Add fixed and exact-trace Frontier surfaces 2026-07-17 10:13:25 +08:00