Blackhole p150 tt-metal: Whisper distil-large-v3 batch-1 TTFT
63.0 ms time-to-first-token, batch 1; vendor marks Blackhole numbers as still-optimizing
Fields
id
benchmarks/ttmetal-p150-whisper-distil-large-v3-b1-ttftMetric
ttft_ms
Value
63
Unit
ms time-to-first-token, batch 1; vendor marks Blackhole numbers as still-optimizing
Model
Whisper distil-large-v3
Methodology
VENDOR demo, same row as the 263.4 tok/s figure. Whisper distil-large-v3, single p150 (Blackhole), batch 1, TT-Metalium v0.65.0-dev20251208. ttft 63 ms. Same Blackhole caveat.
Measured by
vendor
Reproducible
yes
notes
Vendor demo numbers, not a vLLM serving trace. The README states t/s = t/s/u * batch and that vLLM-server performance may differ. LLM rows use input sequence length 128 except Mamba, which accepts any length. Starred Blackhole figures carry the vendor's own caveat that the software is still under active optimization.
Notes
Vendor demo numbers, not a vLLM serving trace. The README states t/s = t/s/u * batch and that vLLM-server performance may differ. LLM rows use input sequence length 128 except Mamba, which accepts any length. Starred Blackhole figures carry the vendor's own caveat that the software is still under active optimization.