docs(bench): nemotron GPU numbers on the GB10#14
Merged
Conversation
parakeet.cpp vs NeMo on the NVIDIA GB10, same clip and methodology as the CPU table: NeMo (PyTorch GPU) RTFx 91.8, parakeet.cpp f32 106.5 (1.16x), q8_0 119.8 (1.30x), transcripts byte-identical (WER 0). The margin is smaller than on CPU because nemotron is RNN-T and NeMo's CUDA-graph greedy decode is fast there. NeMo now runs natively on the GB10 via torch 2.11 plus cu128 (no nvcr container). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds the GPU benchmark for nemotron-3.5-asr-streaming-0.6b to the BENCHMARK.md nemotron section, measured on the NVIDIA GB10 (Grace-Blackwell, sm_121, CUDA 13).
Same clip and 7-pass median methodology as the existing CPU table, both engines on the device, transcripts byte-identical (WER 0). The margin is smaller than the CPU result (2.40-2.52x) because nemotron is RNN-T and NeMo's CUDA-graph greedy decode is fast on GPU; the big GPU wins in this repo are the TDT/hybrid models.
Notable: NeMo now runs natively on the GB10 via torch 2.11 + cu128, so this no longer needs the nvcr NeMo container.
🤖 Generated with Claude Code