devflow / analysis_outputs /T4 /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 0.217 0.168 1.30x 39.3%
32 0.168 0.126 1.33x 39.7%
64 0.250 0.202 1.24x 38.6%
Saved graphs:
- task1_time_comparison.png
- task1_speedup.png
- task1_encoder_cost.png