Your split checks out against the raw runs, and a follow-up run shows where the leftover comes from.
On each model's server: four runs at 256 concurrent requests, two repetitions each. Turkish with scaled output; English prompts padded to the token count of the matching Turkish prompt, with the same scaled output; unpadded English with the scaled output; English at 256 tokens. 2,245 of the 2,248 padded prompts match the Turkish token count exactly, the other three are one token longer.
Padded English runs as fast as Turkish. English Γ· Turkish throughput is 0.992 for Turkish-Gemma-9b-T1, 1.011 for Gemma 4 12B, 1.004 for Ministral 3 14B and 0.998 for Qwen3.8-27B. At equal sequence lengths the language itself costs nothing measurable here; the leftover is sequence length. In the same session it came out at 1.077, 1.061, 1.017 and 0.986.
The other two runs split it:
- Longer prompts at the same scaled output cost all four models a similar 5β8% (1.076, 1.054, 1.077, 1.052).
- Longer outputs with the same unpadded prompts give Ministral and Qwen3.8 about 6% back (0.940, 0.939), because the prefill is spread over more tokens. The two Gemma models get almost nothing back (1.009, 0.996).
That difference lines up with how much KV cache each decoded token reads (BF16 K and V): about 336 KiB for Turkish-Gemma (42 layers Γ 8 KV heads Γ 256), about 330 KiB for Gemma 4 (40 sliding layers Γ 8 Γ 256, plus 8 global layers with one 512-wide K/V head), 160 KiB for Ministral and 64 KiB for Qwen3.8 (16 full-attention layers; its 48 Gated DeltaNet layers keep a fixed-size state). When English output goes from 256 tokens to the scaled length, median TPOT rises 4.5% and 1.2% on the Gemma models and falls 0.7% and 3.1% on Ministral and Qwen3.8. The sliding windows (4,096 and 1,024 tokens) are longer than any Gemma sequence in these runs, all under 800 tokens, so they cap nothing.
The vLLM backend does not look like the common factor: Turkish-Gemma and Ministral both ran on FLASH_ATTN with FlashAttention 3 and sit at opposite ends.
Repeat runs agree within 2.4% in every cell. Raw runs and scripts are in the GitHub repository (projects/tr-serve/results/dolgu, padded_v3.sh, make_padded_prompts.py, padded_summary.py).