Skip to content

[AMD][MI35X] 0526 DSV4 #1568

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
Oseltamivir merged 9 commits into from
May 27, 2026
+13 −4
Merged

[AMD][MI35X] 0526 DSV4 #1568

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
fbddaa3
Update config
1am9trash May 27, 2026
f3870db
Update change log
1am9trash May 27, 2026
a2c9b94
Merge branch 'main' into dsv4-mi355-sgl-0526
1am9trash May 27, 2026
11daefb
Update change log
1am9trash May 27, 2026
44f19c0
Update config
1am9trash May 27, 2026
a618b9e
Update config
1am9trash May 27, 2026
efe0c03
Merge remote-tracking branch 'origin/main' into dsv4-mi355-sgl-0526
1am9trash May 27, 2026
6deed23
Update config
1am9trash May 27, 2026
3ad3afe
Update config
1am9trash May 27, 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 .github/configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1774,7 +1774,7 @@ dsr1-fp4-mi355x-sglang-disagg-mtp:
# image tag, so bumping sglang is just an image tag bump here. Sweeps
# DP-attention on/off and EP=8.
dsv4-fp4-mi355x-sglang:
image: rocm/sgl-dev:rocm720-mi35x-8c3b5aa-20260521-DSv4
image: rocm/sgl-dev:rocm720-mi35x-f96ac98-20260526-DSv4
model: deepseek-ai/DeepSeek-V4-Pro
model-prefix: dsv4
runner: mi355x
Expand All @@ -1786,12 +1786,12 @@ dsv4-fp4-mi355x-sglang:
- isl: 1024
osl: 1024
search-space:
- { tp: 8, dp-attn: true, conc-start: 64, conc-end: 1024 }
- { tp: 8, dp-attn: true, conc-start: 64, conc-end: 4096 }
- { tp: 8, dp-attn: false, conc-start: 1 , conc-end: 32 }
- isl: 8192
osl: 1024
search-space:
- { tp: 8, dp-attn: true, conc-start: 64, conc-end: 512 }
- { tp: 8, dp-attn: true, conc-start: 64, conc-end: 2048 }
- { tp: 8, dp-attn: false, conc-start: 1, conc-end: 32 }

# DSv4 on MI355X via vLLM, using the official vllm/vllm-openai-rocm
Expand Down
2 changes: 2 additions & 0 deletions benchmarks/single_node/dsv4_fp4_mi355x_sglang.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,6 +116,8 @@ python3 -m sglang.launch_server \
--disable-radix-cache \
--attention-backend compressed \
--max-running-requests ${CONC} \
--mem-fraction-static 0.90 \
--swa-full-tokens-ratio 0.1 \
--page-size 256 \
--context-length $MAX_MODEL_LEN \
--chunked-prefill-size 8192 \
Expand Down
8 changes: 8 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3138,8 +3138,16 @@
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1354

- config-keys:
<<<<<<< dsv4-mi355-sgl-0526
- dsv4-fp4-mi355x-sglang
description:
- "Bump image to rocm/sgl-dev:rocm720-mi35x-f96ac98-20260526-DSv4"
- "Add args to avoid kvcache pool full issue on high conc"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1568
=======
- qwen3.5-fp8-h200-sglang
- dsr1-fp8-mi355x-sglang
description:
- "Validates measured-power aggregation pipeline (PR #1558) on both NVIDIA (H200) and AMD (MI355X) hardware — different SMI tools (nvidia-smi vs amd-smi), different CSV schemas (power.draw [W] vs socket_power), same aggregator. No config change. Entry intentionally kept past merge so run-sweep produces canonical agg JSONs with avg_power_w + joules_per_output_token on main for both vendors, seeding the dashboard's day-zero data."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1558
>>>>>>> main
Comment thread
cursor[bot] marked this conversation as resolved.
Outdated
Loading