Spike 9cdbc1fd22 Revert "feat(p800): parameterize GLM5.2 single-node tuning" ...

This reverts commit ba20973beaed07e6f5ccf1be10e9a78e31d614e0.

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

..

dsv4_p800_256k_4k_probe

fix: replace 5 buggy parse_results.py (raw_requests bloat) with shared parse_backend.py wrapper

2026-07-22 03:47:22 +00:00

dsv4_p800_long_context_matrix

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

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

dsv4_p800_max_context_length

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

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

dsv4_p800_sglang

fix: replace 5 buggy parse_results.py (raw_requests bloat) with shared parse_backend.py wrapper

2026-07-22 03:47:22 +00:00

dsv4_p800_sglang_profile

feat(p800): enable operator-level timing in profiling experiment

2026-07-21 02:02:50 +00:00

dsv4_p800_sglang_tp_dp_matrix

feat(ops): add unified bench/deploy layers and P800 profile

2026-08-02 15:36:28 +08:00

dsv4_p800_sglang_tp_dp_official

[Feat] apply validated deployment capacity caps

2026-07-21 11:50:23 +08:00

glm52_w4a8_sglang_tp8_single_node

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

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

qwen3_8b_p800_sglang_tp8

fix: replace 5 buggy parse_results.py (raw_requests bloat) with shared parse_backend.py wrapper

2026-07-22 03:47:22 +00:00

qwen3_235b_p800_sglang_tp8

fix: replace 5 buggy parse_results.py (raw_requests bloat) with shared parse_backend.py wrapper

2026-07-22 03:47:22 +00:00

P800_vs_H20_DIAGNOSIS_PLAN.md

feat: add P800 vs H20 diagnosis plan for performance gap analysis

2026-07-20 05:30:29 +00:00