Add Qwen3.5 GB300 SGLang recipes#2
Draft
nvpohanh wants to merge 2 commits into
Draft
Conversation
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
Contributor
Author
|
[by Codex] This draft PR is subject to change because SemiAnalysisAI/InferenceX#2121 has not been merged yet. The recipes currently mirror source commit |
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
nvpohanh
changed the title
5 tasks
faradawn
reviewed
Jul 17, 2026
Comment on lines
+202
to
+213
| benchmark: | ||
| type: custom | ||
| command: bash /infmax-workspace/benchmarks/multi_node/agentic_srt.sh | ||
| env: | ||
| INFMAX_CONTAINER_WORKSPACE: /infmax-workspace | ||
| RESULT_DIR: /logs/agentic | ||
| PORT: "8000" | ||
| IS_MULTINODE: "true" | ||
| WEKA_LOADER_OVERRIDE: semianalysis_cc_traces_weka_062126_256k | ||
| AIPERF_USE_DYNAMO_CONV_AWARE_ROUTING: "1" | ||
| AIPERF_DATASET_MMAP_CACHE_DIR: "/aiperf_mmap_cache" | ||
| HF_HUB_CACHE: "/hf_hub_cache" |
Collaborator
There was a problem hiding this comment.
What is the benchmark type of custom? Is it using ai perf or agentx load gen?
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
[by Codex]
Description
Adds 19 Qwen3.5-397B-A17B GB300 SGLang recipes:
The exports are pinned to the exact successful workflow commits:
f0f925f5ccb6a2eb4915397e0eaad0362f188cc5baeb99b637333ad0ad0cf5d5834239bdae3cfa6931506a734d536307fc4eb1eb404cf45804d91b41The agentic recipes use
agenticfor the workload directory instead of a fixed input/output sequence-length label. The/infmax-workspacereferences are container-local paths used by the public InferenceX AgentX harness, not cluster host paths.This PR remains a draft because InferenceX PR 2121 has not merged and its nine agentic recipes may change.
Validation:
srtctl dry-runfor all 19 files using NVIDIA/srt-slurm v1.0.25 (3435776)python scripts/update_recipe_table.py; the existing Qwen3.5 multi-node support-matrix row remains currentType of change
Checklist
recipes/<single-node|multi-node>/<model>/<GPU>/<framework>/path.python scripts/update_recipe_table.pyhas been run and the README table is up to date.srtctl dry-runlocally or by CI.