devflow / analysis_outputs /T16 /task1_kv_cache.txt
bhsinghgrid's picture
Update app/inference + ablation task outputs
27f26fd verified
TASK 1 — KV CACHE BENCHMARK
========================================
has_generate_cached=True
memory_profile=N/A (CPU/MPS)
src_len standard(s) cached(s) speedup encoder%
16 0.855 0.549 1.56x 39.2%
32 0.679 0.499 1.36x 41.2%
64 1.069 0.732 1.46x 40.0%
Saved graphs:
- task1_time_comparison.png
- task1_speedup.png
- task1_encoder_cost.png