Skip to content

[AMD] Qwen3.5-FP8 MI355X SGLang disagg perf tuning: Docker image update / Qwen3.5-FP8 MI355X SGLang disagg 性能调优 更新Docker image #2094

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
adibarra merged 5 commits into from
Jul 17, 2026
+18 −3
Merged

[AMD] Qwen3.5-FP8 MI355X SGLang disagg perf tuning: Docker image update / Qwen3.5-FP8 MI355X SGLang disagg 性能调优 更新Docker image #2094

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
db4487a
[AMD] Qwen3.5-FP8 MI355X SGLang disagg: image bump, node fix, runner …
Jul 6, 2026
f557d68
Remove unintended files
Jul 6, 2026
2d0d7e7
Merge branch 'main' into chang/qwen3.5-mi355-di-perf-tuning-rebased
1am9trash Jul 14, 2026
c8b5597
Change PR link to #2094
1am9trash Jul 14, 2026
9418f92
Merge branch 'main' into chang/qwen3.5-mi355-di-perf-tuning-rebased
1am9trash Jul 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -404,7 +404,7 @@ qwen3.5-fp8-mi355x-atom-mtp:
- { tp: 8, ep: 1, conc-start: 4, conc-end: 256, spec-decoding: mtp }

qwen3.5-fp8-mi355x-sglang-disagg:
image: lmsysorg/sglang-rocm:v0.5.11-rocm700-mi35x-20260511
image: lmsysorg/sglang:v0.5.14-rocm720-mi35x
model: Qwen/Qwen3.5-397B-A17B-FP8
model-prefix: qwen3.5
runner: mi355x-disagg
Expand All @@ -421,7 +421,7 @@ qwen3.5-fp8-mi355x-sglang-disagg:
search-space:
# Matches qwen3.5-fp8-mi355x-sglang TP8/EP1 low-concurrency sweep
- spec-decoding: "none"
conc-list: [ 8, 16, 32, 64, 128, 256, 512 ]
conc-list: [ 8, 16, 32, 64, 128 ]
prefill:
num-worker: 1
tp: 8
Expand Down Expand Up @@ -452,7 +452,7 @@ qwen3.5-fp8-mi355x-sglang-disagg:
# MoRI is added to is_deepep_class_backend() or shared-slot
# accounting is reconciled.
- spec-decoding: "none"
conc-list: [ 8, 16, 32, 64, 128, 256, 512 ]
conc-list: [ 8, 16, 32, 64, 128 ]
prefill:
num-worker: 1
tp: 8
Expand Down
6 changes: 6 additions & 0 deletions configs/runners.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,6 +126,12 @@ labels:
- mi355x-amds_06
- mi355x-amds_07
- mi355x-amds_08
- mi355x-amds_12
- mi355x-amds_14
- mi355x-amds_16
- mi355x-amds_17
- mi355x-amds_18
- mi355x-amds_19
gb200:
- gb200-nv_0
- gb200-nv_1
Expand Down
9 changes: 9 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4918,3 +4918,12 @@
- "Image: vllm/vllm-openai:nightly-dev-x86_64-cu13.0.1-904e4ec"
- "B300: GPU-resident TP4/TP8 at conc [1,2,4,6,8,12,16,20,24,28,32] and DEP8 at conc [32,64,96,128,160,192,196,224,228] (max-num-batched-tokens 16384, long-prefill-token-threshold 4096, gpu-memory-utilization 0.92); TP4 SimpleCPU lazy-offload at conc [28,32,36,40]; DEP4 at conc [8,16,24,32,40,48,56,64,72] with both SimpleCPU and Mooncake 0.3.11.post1."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2241

- config-keys:
- qwen3.5-fp8-mi355x-sglang-disagg
description:
- "Bump Qwen3.5-FP8 MI355X SGLang disagg image from lmsysorg/sglang-rocm:v0.5.11-rocm700-mi35x-20260511 to lmsysorg/sglang:v0.5.14-rocm720-mi35x (ROCm 7.0 → 7.2, sglang v0.5.11 → v0.5.14)."
- "Fix disagg SLURM exclude list: add mia1-p01-g09 (broken pyxis) to submit.sh — was missing from multi-node path, causing prefill worker 503 failures."
- "Expand mi355x-disagg runner pool from 3 to 9 nodes."
- "Concurrency sweep: 1K1K and 8K1K both [ 8, 16, 32, 64, 128 ]."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2094