perf-changelog: re-run DSR1 SGLang agg configs (B200/B300, FP8/FP4, no-MTP/MTP) (#1502)

* perf-changelog: re-run DSR1 SGLang agg configs to pick up tokenizer fix

Re-runs DSR1 SGLang agg configs on B200/B300 (FP8/FP4, no-MTP/MTP) to
pick up the tokenizer fix from #1381.

* perf-changelog: set PR link to #1502

* launcher(b300-nv): drop nodelist pinning; restore perf-changelog entries

- runners/launch_b300-nv.sh: remove --nodelist=b300-[001-006,008-012,017-020] from salloc so jobs can land on any healthy B300 node.
- perf-changelog.yaml: restore ~18 entries that were unintentionally dropped during a prior rebase; net effect of this branch is now just the new DSR1 SGLang agg re-run entry.

* perf-changelog: sync to origin/main and append DSR1 re-run entry at end

* Update perf-changelog.yaml

---------

Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>

Author: Ankur-singh

perf-changelog.yaml

@@ -2997,3 +2997,14 @@
   description:
     - "Add MTP/EAGLE speculative-decoding sibling for dsr1-fp8-h200-sglang (model: deepseek-ai/DeepSeek-R1-0528) on lmsysorg/sglang:v0.5.12-cu130 — TP=8, EP=1, search-space conc 4..64 on 1k1k + 8k1k"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1523
+
+- config-keys:
+    - dsr1-fp8-b200-sglang
+    - dsr1-fp8-b300-sglang
+    - dsr1-fp4-b200-sglang
+    - dsr1-fp4-b300-sglang
+    - dsr1-fp8-b200-sglang-mtp
+    - dsr1-fp8-b300-sglang-mtp
+  description:
+    - "Re-run DSR1 SGLang agg configs (B200/B300, FP8/FP4, no-MTP/MTP) — picks up tokenizer fix from #1381"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1502

runners/launch_b300-nv.sh

@@ -331,9 +331,7 @@ else
         fi
     )
 
-    # Pin to one of the known-good B300 nodes; others have hardware/network
-    # issues that cause benchmarks to hang or fail to start.
-    salloc --partition=$SLURM_PARTITION --account=$SLURM_ACCOUNT --nodelist=b300-[001-006,008-012,017-020] -N 1 --gres=gpu:$TP --exclusive --time=180 --no-shell --job-name="$RUNNER_NAME"
+    salloc --partition=$SLURM_PARTITION --account=$SLURM_ACCOUNT -N 1 --gres=gpu:$TP --exclusive --time=180 --no-shell --job-name="$RUNNER_NAME"
     JOB_ID=$(squeue --name="$RUNNER_NAME" -u "$USER" -h -o %A | head -n1)
 
     srun --jobid=$JOB_ID \