yy-fighting 21fcca5d16 b300-equivalent matrix: dual-plan (TP2PP4-D vs E7b) full B300 scenario replication on 60.8 - 41 valid points, divide at C=8, E7b usable window <=C8 (MRR16+graph-drop), boundary 256K/512K/896K TP2PP4-only, 4-5x absolute gap vs B300 narrowing to ~2x at boundary prefill; hicache host-layer cold-cache pitfall documented; in-service container preserved-renamed-restored and verified (09-10)

2026-09-10 17:13:50 +08:00

..

910c

fix(910c/glm52): 镜像与 client 修正 - 部署在 910c.2 的 GLM5.2-tuned 镜像

2026-08-03 17:22:04 +08:00

h20

Add vLLM TP×DP matrix benchmarking scripts and Docker support

2026-07-23 02:06:47 +00:00

h200

docs: consolidate project docs (dedup, relocate, expand 910C client guide)

2026-07-29 11:52:42 +08:00

p800

Revert "feat(p800): parameterize GLM5.2 single-node tuning"

2026-08-20 07:33:38 +00:00

pro6000

b300-equivalent matrix: dual-plan (TP2PP4-D vs E7b) full B300 scenario replication on 60.8 - 41 valid points, divide at C=8, E7b usable window <=C8 (MRR16+graph-drop), boundary 256K/512K/896K TP2PP4-only, 4-5x absolute gap vs B300 narrowing to ~2x at boundary prefill; hicache host-layer cold-cache pitfall documented; in-service container preserved-renamed-restored and verified (09-10)

2026-09-10 17:13:50 +08:00

TEMPLATE

Add num_prompts = 5×concurrency convention and update all experiments

2026-07-09 09:26:41 +00:00

ADAPTIVE_CONCURRENCY_USAGE.md

rewrite README, add new platform onboarding guide, fix broken scripts/common paths

2026-07-17 06:18:05 +00:00