[WIP][NV] add glm5-fp4-gb200-dynamo-sglang

[hshrivastava-droid]

Note

Low Risk
Benchmark and CI launcher/config only; no application runtime or auth changes. Main review surface is recipe/topology correctness and cluster resource assumptions.

Overview
Adds GLM-5 NVFP4 disaggregated Dynamo + SGLang benchmark coverage on GB200, mirroring the existing GB300 glm5 entry pattern.

nvidia-master.yaml introduces glm5-fp4-gb200-dynamo-sglang with fixed-seq-len scenarios for 8k1k and 1k1k: wide-EP decode (TP=32) max-throughput topologies (4p–10p prefill variants) and per-node TP=4 low-latency decode workers, each wired to a concrete CONFIG_FILE under recipes/sglang/glm5/gb200-fp4/.

New srt-slurm recipe YAMLs (ported from upstream gb200-fp4/glm5.yaml, one file per topology) live under benchmarks/multi_node/srt-slurm-recipes/sglang/glm5/gb200-fp4/ with Slurm resources, Dynamo frontend, nixl disagg, and tuned sglang_config / sa-bench concurrency per recipe.

runners/launch_gb200-nv.sh maps glm5 + fp4 to lustre GLM-5-NVFP4 and overlays the glm5 recipe tree onto NVIDIA/srt-slurm (sa-submission-q2-2026). perf-changelog.yaml documents the new config key.

^{Reviewed by Cursor Bugbot for commit ba74df2. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=27575447726
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=27575447726

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit aa5f207. Configure here.}

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=27652197300
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=27652197300

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=27652967695
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=27652967695

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=27653968669
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=27653968669