Skip to content

MODEL-NEMOTRON-H-ABI-A2P: no speed number exists for Nemotron-3.5-Lightning-30B now that the device token gate passes #1250

Description

@localai-bot

MODEL-NEMOTRON-H-ABI-A2P's A3 token gate now reads TOKEN MATCH: 96/96 over 3 prompt(s) (full rows=3, short rows=0, mode=decode) STRICT PASS on GB10 sm_121a under the #1157 fix (PR #1221), against the released nemotron-3.5-lightning-30b-nvfp4 at revision 29f2d1746d8f41e316523194b19018707749b1b1, with the fix reverted reading 4/24 on the same binary. Correctness is therefore established on the device, and no speed number exists for this model on any axis.

docs/BENCHMARKS.md carries the row as "No speed number, by the unit's own rule". This issue owns producing the first ones: a same-workload comparison against the pinned vLLM oracle (vllm_commit = 5559679229bc961848b121ccdeaa8fa5d79bec98) on dgx:gpu0, inside an rc lease, on the identical checkpoint, prompts, token counts, batching, concurrency and sampling, with vLLM in its production configuration as the denominator and never --enforce-eager.

The gate run already says where the number will land and why, and the causes are named rather than guessed:

The gate legs measured 264.4 s engine load and 342.61 / 328.19 / 327.51 s for 32 tokens each, i.e. about 10.3 s per output token at batch 1. That is a measurement to record honestly with its causes, not a ceiling.

Two comparability facts this issue has to control for. --gpu-memory-utilization 0.92 does NOT size our KV pool -- the profile run is unimplemented (#83) and the pool falls back to 256 blocks -- so the pool is sized explicitly on our side and the oracle's KV budget is matched to it, or the memory axis is not like-for-like. And the oracle side is unproven for a MODEL RUN inside a lease: #1185 established build, install, import and torch.cuda.is_available() only, and the recorded failure mode of the step after torch.compile on this host is a reboot of the box. If the oracle cannot run, the numerator-only figures are recorded as ungated and never as a ratio.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions