Commit Graph

  • b3ead2cb77 untrack tp*_dp* outputs again; fix gitignore pattern (add platform/experiment level) yy-fighting 2026-07-17 07:13:48 +00:00
  • 3b1539d446 fix over-corrected scripts/common paths (4 levels -> 3) in 12 scripts yy-fighting 2026-07-17 07:09:40 +00:00
  • b01640aa20 commit only aggregated adaptive results; untrack tp*_dp* raw outputs and metrics yy-fighting 2026-07-17 06:28:55 +00:00
  • 8652a685e6 rewrite README, add new platform onboarding guide, fix broken scripts/common paths yy-fighting 2026-07-17 06:18:05 +00:00
  • 90f0257ae0 update result SSKJ Dev 2026-07-17 02:19:22 +00:00
  • ff218bdeb3 enable TTFT group skip for all add16 benchmarks SSKJ Dev 2026-07-17 02:04:05 +00:00
  • 0591c401ab update stop method SSKJ Dev 2026-07-16 13:02:29 +00:00
  • 589d3b079d enable initial backoff for all add16 benchmarks SSKJ Dev 2026-07-16 09:05:37 +00:00
  • c2a3024a1b update SEARCH_INITIAL_BACKOFF_CONCURRENCIES SSKJ Dev 2026-07-16 08:52:29 +00:00
  • 58ed6ea633 fix P800 bench_serving P95 yy-fighting 2026-07-16 07:49:32 +00:00
  • fd03460e19 Keep raw_outputs .jsonl in git for cloud-side result storage yy-fighting 2026-07-16 06:52:10 +00:00
  • 136fc80a38 Merge branch 'main' of https://gitee.com/yy-fighting/sskj yy-fighting 2026-07-16 06:49:52 +00:00
  • 0fdd3749c7 Add P800 sglang TP/DP matrix experiment yy-fighting 2026-07-16 06:49:21 +00:00
  • 20cb4e35c2 update SSKJ Dev 2026-07-16 06:25:00 +00:00
  • 8f89cf6dc2 Merge branch 'main' of https://gitee.com/yy-fighting/sskj yy-fighting 2026-07-16 05:18:58 +00:00
  • dcb8cd2131 feat(adaptive): add TTFT SLO early-stop and fix relative paths for h20 experiments SSKJ Dev 2026-07-16 05:15:51 +00:00
  • 18ded8e15d Merge branch 'main' of https://gitee.com/yy-fighting/sskj yy-fighting 2026-07-16 05:13:38 +00:00
  • a4e38b9e33 Reorganize experiments into hardware-specific subdirectories SSKJ Dev 2026-07-16 04:11:07 +00:00
  • 90fc378d2b Add H20 TP×DP matrix experiments for vLLM and SGLang SSKJ Dev 2026-07-16 03:43:58 +00:00
  • 9d7f3d7f87 docs(envs): add uv environment setup guide Quantong Qiu 2026-07-14 10:59:15 +00:00
  • 5d2f1b2d9a docs(envs): add envs README and track deployment guides Quantong Qiu 2026-07-14 10:53:38 +00:00
  • 5405d002fc chore: remove legacy benchmark files and scripts Quantong Qiu 2026-07-14 10:47:09 +00:00
  • e0ae0715b1 feat(adaptive): add RESUME_RUN_ID resume support and rename DSL to OSL Quantong Qiu 2026-07-14 10:41:01 +00:00
  • 60826dda09 add run_adaptive_concurrency_add16 iiGray 2026-07-13 17:26:33 +08:00
  • a7f453b997 feat: add run_bench.sh and fix config for dsv4_pro6000_sglang_tp_dp_matrix Root 2026-07-13 05:22:31 +00:00
  • 819850c4a1 Update README.md with new experiments and RTX 6000D platform Quantong Qiu 2026-07-13 03:04:46 +00:00
  • d904d663a4 Add dsv4_pro6000_vllm_tp_dp_matrix experiment for RTX 6000D Quantong Qiu 2026-07-13 02:59:33 +00:00
  • 372ff08eea Add master orchestrator script for sequential benchmark execution Quantong Qiu 2026-07-13 02:46:15 +00:00
  • 302d1a9822 Rename DSL to OSL (Output Sequence Length) in dsv4_pro6000 experiment Quantong Qiu 2026-07-13 02:28:11 +00:00
  • 8ebe963269 Add dsv4_pro6000_sglang_tp_dp_matrix experiment for RTX 6000D Quantong Qiu 2026-07-13 02:18:34 +00:00
  • cf7a12932e bench: add adaptive run heartbeat monitor Root User 2026-07-11 13:04:35 +00:00
  • 5e95cee1a0 bench: add adaptive concurrency search Root User 2026-07-11 06:11:19 +00:00
  • d783143ddb vllm tp_dp_matrix: dockerize deployment and fix missing DOCKER_CLIENT_IMAGE export Root User 2026-07-10 08:44:38 +00:00
  • 4d5b6a77ca Add custom benchmark setup for vLLM TP=8 on dsv4 H200 Quantong Qiu 2026-07-10 09:40:10 +00:00
  • cd539c4d7d chore: add tsv files to .gitignore yy-fighting 2026-07-10 09:20:41 +00:00
  • b5d409ea3d chore: add experiments/*/runtime/ to .gitignore yy-fighting 2026-07-10 09:19:41 +00:00
  • a388358b37 fix(sglang-tp-dp-matrix): export DOCKER_IMAGE/USE_DOCKER_CLIENT and add persistent container support yy-fighting 2026-07-10 07:05:36 +00:00
  • db00c1b1ac Add custom benchmark setup for vLLM TP=2 on dsv4_h200 Quantong Qiu 2026-07-10 09:06:10 +00:00
  • e62ab7c970 sglang tp_dp_matrix: export MODEL_PATH and RESULT_BASE for bash -c subshells yy-fighting 2026-07-10 04:57:22 +00:00
  • 58a3616872 sglang tp_dp_matrix: export DATASET_PATH for bash -c subshells yy-fighting 2026-07-10 04:07:14 +00:00
  • 605b976fb8 sglang tp_dp_matrix: fix empty DATASET_PATH causing docker invalid spec yy-fighting 2026-07-10 03:13:11 +00:00
  • 4ea6e92b42 sglang tp_dp_matrix: fix timeout calling bash function (rc=127) yy-fighting 2026-07-10 02:51:29 +00:00
  • 938b2f1e88 workflow: document what to commit for each experiment yy-fighting 2026-07-10 02:22:30 +00:00
  • 666c583844 vllm tp_dp_matrix: add final results (report, results.json, comparison, scenarios) yy-fighting 2026-07-10 02:20:36 +00:00
  • 06cfab20d2 sglang tp_dp_matrix: keep 1M ISL (128 Y, 256 P) in scope yy-fighting 2026-07-10 02:18:34 +00:00
  • f7f4e928d9 sglang tp_dp_matrix: exclude 1M ISL from mandatory matrix per current scope yy-fighting 2026-07-10 02:17:38 +00:00
  • 7852dd2040 sglang tp_dp_matrix: run SGLang server/client in Docker on H200 yy-fighting 2026-07-10 02:17:00 +00:00
  • db419e17b8 dsv4_h200_sglang_tp_dp_matrix: sample only low/high concurrency, use RUNTIME_BASE for self-contained runtime files Root User 2026-07-09 15:36:03 +00:00
  • 90d1738605 Merge branch 'main' of https://gitee.com/yy-fighting/sskj yy-fighting 2026-07-09 15:24:08 +00:00
  • 31731ebb75 dsv4_h200_vllm_tp_dp_matrix: export CONCURRENCY_SAMPLES so generate_scenarios.py sees it yy-fighting 2026-07-09 15:23:57 +00:00
  • 8d61e682cd add dsv4_h200_sglang_tp_dp_matrix experiment (Docker-based SGLang TP×DP matrix) Root User 2026-07-09 14:49:31 +00:00
  • 0ae1ea0a9f dsv4_h200_vllm_tp_dp_matrix: fix output naming, parser/compat, add Docker startup option yy-fighting 2026-07-09 12:33:52 +00:00
  • 0aee540c67 dsv4_h200_vllm_tp_dp_matrix: single server per config, OOM/restart handling, DRY_RUN/GRID_LIMIT, include 1M yy-fighting 2026-07-09 10:50:59 +00:00
  • 329d4c3975 dsv4_h200_vllm_tp_dp_matrix: use vLLM internal DP LB, drop proxy/supervisor yy-fighting 2026-07-09 10:28:50 +00:00
  • 59dbadb110 add dp_proxy for vLLM DP, write kv_cache_analysis.md, fix DP bench port yy-fighting 2026-07-09 10:19:30 +00:00
  • 5898d578ed dsv4_h200_vllm_tp_dp_matrix: allow MATRIX_FILE env override yy-fighting 2026-07-09 10:02:45 +00:00
  • 39326eaf4a remove partial smoke test artifacts from killed run yy-fighting 2026-07-09 10:02:03 +00:00
  • 15b5489535 dsv4_h200_vllm_tp_dp_matrix: use minimal official vLLM args, no EP, Y-only, exclude 1M yy-fighting 2026-07-09 10:01:51 +00:00
  • 04a384b265 add dsv4_h200_vllm_tp_dp_matrix experiment (TP×DP matrix with Y-only mode, 1M excluded) yy-fighting 2026-07-09 09:55:18 +00:00
  • 1482601ae5 Add num_prompts = 5×concurrency convention and update all experiments yy-fighting 2026-07-09 09:26:24 +00:00
  • a1da95ef44 Scale P800 long-context matrix to concurrency=1 for stability Quantong Qiu 2026-07-09 05:59:28 +00:00
  • 46e05a57a4 Re-enable chunked prefill for P800 long-context matrix stability Quantong Qiu 2026-07-09 05:13:04 +00:00
  • 59f480b1bc Disable chunked prefill and speculative decoding in P800 long-context matrix Quantong Qiu 2026-07-09 04:47:59 +00:00
  • 90eecc4ede Add P800 long-context matrix experiment (64k/128k) for DeepSeek-V4-Flash-INT8 Quantong Qiu 2026-07-09 04:45:04 +00:00
  • b1b5f50f56 results(p800): max context length exploration run 20260709-033134 Quantong Qiu 2026-07-09 04:08:40 +00:00
  • 06549d8faf cleanup(p800): remove local debugging artifacts from dsv4_p800_sglang/results Quantong Qiu 2026-07-09 03:30:58 +00:00
  • 3694614dd9 feat(p800): add max context length exploration experiment Quantong Qiu 2026-07-09 03:30:09 +00:00
  • 8324d944f2 fix(p800): define RUN_ID/RESULT_ROOT/LOG_DIR in start_server.sh Quantong Qiu 2026-07-09 02:53:38 +00:00
  • 7e614fb702 Add DSpark backend to long-context matrix experiment yy-fighting 2026-07-09 02:36:57 +00:00
  • 278653b6a6 Add three-way comparison: MTP vs DSpark vs default yy-fighting 2026-07-09 01:42:46 +00:00
  • 7d2ed7f05d Add vLLM+MTP speculative decoding benchmark vs default on H200 yy-fighting 2026-07-08 16:13:01 +00:00
  • a56c995091 results(max-context): complete H200 max context length exploration run 20260708-143534 yy-fighting 2026-07-08 15:33:48 +00:00
  • 4658e36b1e Fix P800 baseline server startup issues yy-fighting 2026-07-08 15:27:31 +00:00
  • f6a45f1ed8 Add P800 long-context matrix and tune benchmark/health settings yy-fighting 2026-07-08 15:02:22 +00:00
  • 539b3bc539 Merge branch 'main' of https://gitee.com/yy-fighting/sskj yy-fighting 2026-07-08 14:45:00 +00:00
  • cd0b083a10 results(vllm-dspark-vs-default): complete TTFT comparison run 20260708-142121 yy-fighting 2026-07-08 14:35:14 +00:00
  • 27ceaac47f results(long-context-matrix): complete 64k/128k/256k matrix run 20260708-100016; use common scripts yy-fighting 2026-07-08 11:21:15 +00:00
  • 9b135aa4ff revert: remove intermediate matrix results committed by mistake (again) yy-fighting 2026-07-08 11:06:54 +00:00
  • 80959cf765 docs: move SLO_STANDARDS.md from scripts/ to docs/; update references yy-fighting 2026-07-08 11:06:49 +00:00
  • ccf65e745b revert: remove intermediate matrix results committed by mistake yy-fighting 2026-07-08 11:04:23 +00:00
  • 9b485c05f7 cleanup(scripts): remove unused legacy scripts; update README and workflow docs yy-fighting 2026-07-08 11:04:16 +00:00
  • f51697aed6 refactor(common): remove duplicated parse/compare/warmup from existing experiments yy-fighting 2026-07-08 10:49:27 +00:00
  • a127cf7ef0 refactor(common): centralize parse/compare/warmup; add TEMPLATE and EXPERIMENT_GUIDE yy-fighting 2026-07-08 10:48:43 +00:00
  • be94b8e7ef Add P800 256k/4k long-context probe and baseline w8a8_int8 server mode yy-fighting 2026-07-08 10:30:05 +00:00
  • 868ebc6cdf feat(long-context-matrix): add SGLang vs vLLM long-context matrix experiment yy-fighting 2026-07-08 10:09:32 +00:00
  • cd2ba29d49 feat(256k-4k-probe): verify SGLang/vLLM can serve 256k+4k without OOM yy-fighting 2026-07-08 09:59:05 +00:00
  • 0f9399baf6 feat(64k): add SGLang vs vLLM 64k-context comparison and results run 20260708-092556 yy-fighting 2026-07-08 09:44:13 +00:00
  • ee954d7409 fix(sglang-vs-vllm): use jq for metadata update; add results run 20260708-083346 yy-fighting 2026-07-08 09:21:49 +00:00
  • 5eb605b7a2 feat: support resuming interrupted SGLang vs vLLM runs yy-fighting 2026-07-08 08:42:21 +00:00
  • fd0474099a chore: do not commit partial SGLang vs vLLM results while run is in progress yy-fighting 2026-07-08 08:36:13 +00:00
  • 19d336de08 feat: add max context length exploration experiment yy-fighting 2026-07-08 08:35:56 +00:00
  • b12039599d chore: remove partial SGLang vs vLLM run that failed mid-way yy-fighting 2026-07-08 08:33:37 +00:00
  • 0bb8adf2d9 feat: add SLO status field to per-backend reports and results.json yy-fighting 2026-07-08 08:28:37 +00:00
  • b5b636236d docs: require server launch args to be recorded in results.json yy-fighting 2026-07-08 08:22:33 +00:00
  • 162168da3c feat: record exact server launch args in results.json for reproducibility yy-fighting 2026-07-08 08:21:55 +00:00
  • 69756c598c fix: ignore nested backend raw_outputs/logs and remove accidentally committed intermediate files yy-fighting 2026-07-08 08:15:39 +00:00
  • 5d1cd9c266 feat: add vLLM+DSpark vs vLLM-default TTFT comparison experiment yy-fighting 2026-07-08 08:15:02 +00:00
  • 3cf8b8f0d7 fix: use --context-length instead of --max-model-len for SGLang server yy-fighting 2026-07-08 07:57:15 +00:00
  • 06b3398ad0 feat: add ShareGPT dataset scenarios to SGLang vs vLLM comparison yy-fighting 2026-07-08 07:42:05 +00:00
  • e6d9e99b6f feat: add SGLang vs vLLM controlled comparison experiment yy-fighting 2026-07-08 07:34:34 +00:00