Repository navigation
[GLM-5.3 GB300] add Dynamo-SGLang AgentX agg and disagg recipes with power / [GLM-5.3 GB300] 新增 Dynamo-SGLang AgentX 聚合与分离部署配方并采集功耗 - #4706
edwingao28 wants to merge 11 commits into
Conversation
中文:采集 GLM-5.2 GB300 Dynamo-SGLang AgentX 功耗
|
Thanks for the contribution!
中文感谢你的贡献!
|
1238f20 to
1a66b16
Compare
There was a problem hiding this comment.
Besides the inline finding, I checked the new GB300 GLM-5.2 PowerRule in infx/launch/drivers/srt/power.py. Its Match arguments are in the right order (prefixes, precisions, frameworks, then agentic=True). The rule also matches the existing GB200 GLM-5.2 rule exactly, which doesn't set require=True either, so leaving that flag off follows the existing pattern.
Extended reasoning...
I compared the new rule with Match's field order in infx/launch/policy.py and with the GB200 srt-multi lane, which already has an identical GLM-5.2 FP4 dynamo-sglang AgentX rule that doesn't set require.
|
View unofficial run (performance): https://inferencex.semianalysis.com/inference?unofficialRun=41407333903 View unofficial run (accuracy): https://inferencex.semianalysis.com/evaluation?unofficialRun=41407333903 |
中文:将 main 合并到 GLM-5.3 GB300 Dynamo-SGLang AgentX
中文:新增 GLM-5.3 FP4 GB300 Dynamo-SGLang AgentX 聚合配置
中文:新增 GLM-5.3 FP4 GB300 Dynamo-SGLang AgentX 分离式配置
中文:将 main 合并到 GLM-5.3 GB300 Dynamo-SGLang AgentX
|
/use 41407333903 |
|
@edwingao28 staged run 41407333903. This run remains available across future |
中文:更正 GLM-5.3 GB300 changelog 中的功耗规则描述。
中文:将 main 合并到 GLM-5.3 GB300 Dynamo-SGLang AgentX。
Summary
GLM-5.3 NVFP4 has AgentX coverage only on B300 SGLang (
glm5.3-fp4-b300-sglang-agentic-mtp). No config runsnvidia/GLM-5.3-NVFP4on GB300, and thegb300-nvrunner has no path for its weights. GLM-5.3 therefore has no GB300 Dynamo-SGLang points and no measured GB300 power.Changes:
glm5.3/sglang/gb300-fp4/agentx/(new recipes), ported from the GLM-5.2 GB300 Dynamo-SGLang recipes:agg-variants.yaml: one TP4 worker and one TP8 worker, each at conc 1.disagg-variants.yaml: one to four PP4 prefill workers with TP4, TP8 or TP16 decode, six points at conc 30 to 264.nvidia/GLM-5.3-NVFP4at revisione3b8f9f2with NEXTN MTP (3 steps, 4 draft tokens) and DRAM HiCache KV offload.nvidia-master.yaml: addsglm5.3-fp4-gb300-dynamo-sglang-agentic-aggandglm5.3-fp4-gb300-dynamo-sglang-agentic-disaggoncluster:gb300-nv.lmsysorg/sglang:nightly-dev-20261021-c1c287a4. The disagg key usesnightly-dev-20261016-a93f16f0, the image of the published GLM-5.2 GB300 disagg points.power: true, so the GB300 multi-node default power collection from [PowerX] collect multinode power by default / [PowerX] 默认采集多节点功耗 #3670 treats GPU power as required, not best effort.runners.yaml: mapsGLM-5.3-NVFP4to thedata-modelsroot ongb300-nv.perf-changelog.yaml: one block listing both keys.No launcher or
infx/code changes. All other configs are unchanged.Results: sweep 41407333903, attempt 1, source
26d2411f3, GB300, AgentX agentic-coding traces. Every row comes from this run. The baseline is the published GLM-5.2 GB300 Dynamo-SGLang point with the same topology and concurrency, from 2026-10-20.InvalidInferenceResultError.Testing:
python -m infx.matrix.changed --base origin/mainat the current heade4904851alists only the two new keys (8 points). Their point fingerprints equal those of run 41407333903, so the run still covers this head.Limits:
glm-5.3-nvfp4curve (mean 2.94, Select golden AL curves by verifier and add SPEED-Bench collectors / 按验证器选择黄金 AL 曲线并新增 SPEED-Bench 收集脚本 #4663). These points therefore assume a 1.7% higher mean acceptance length than a rerun on main would. GLM-5.3 points measured before Select golden AL curves by verifier and add SPEED-Bench collectors / 按验证器选择黄金 AL 曲线并新增 SPEED-Bench 收集脚本 #4663 carry the same offset.glm5.3under the GLM-5.2 display model. These points join the published GLM-5.2 points in the GB300 Dynamo-SGLang series, as the two models' B300 SGLang points already do. The GLM-5.2 rows stay in the database.Delivery:
/use 41407333903is posted. Merging reuses this run and starts no GPU job.PR checklist and change type
Type of Change
Checklist
python -m infx.matrix.changed --base origin/mainlists affected config keys, I have appended one new entry covering them to the physical end ofinferencex-e2e/perf-changelog.yaml; if it lists none, I have added none. I have not edited historical entriesinferencex-e2e/perf-changelog.yamlentry, it carries exactly one primary sweep label (a maintainer applies it on fork PRs):full-sweep-fail-fast(recommended),full-sweep-enabled, ornon-canary-full-sweep-enabled. Optional modifiersall-evals,evals-only, andagentx-fastrequire a primary label; the last two block reuse while applied.OWNER/MEMBER/COLLABORATOR) has commented/use <run_id>(or the legacy/reuse-sweep-run) on this PR. Do this only once there is a final full sweep that is all green with evals passing, since after this comment the primary sweep label will no longer automatically kick off new sweeps. Remove and re-add the primary sweep label to force a new sweep.