Skip to content

[AMD][MI355X] Update DeepSeek V4 Pro MoRI to SGLang ROCm 10 nightly / [AMD][MI355X] 更新 DeepSeek V4 Pro MoRI 的 SGLang ROCm 10 nightly 镜像 #4571

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 3 commits into from
Oct 28, 2026
+10 −1
Merged

[AMD][MI355X] Update DeepSeek V4 Pro MoRI to SGLang ROCm 10 nightly / [AMD][MI355X] 更新 DeepSeek V4 Pro MoRI 的 SGLang ROCm 10 nightly 镜像 #4571

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a4d66a6
perf(amd): update MI355X DeepSeek V4 MoRI to ROCm 10 nightly
Duyi-Wang Oct 27, 2026
403fcf1
chore: link MI355X image refresh changelog to PR
Duyi-Wang Oct 27, 2026
4dbb701
Merge branch 'main' into config/mi355x-dsv4-mori-sglang-rocm10-nightly
billishyahao Oct 28, 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
2 changes: 1 addition & 1 deletion inferencex-e2e/configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1197,7 +1197,7 @@ dsv41flash-fp4-mi325x-vllm-agentic-dspark:
- { tp: 2, kv-offloading: none, spec-decoding: mtp, conc-list: [1, 2, 4, 8, 16, 32], srt-recipe: agentic.yaml }

dsv4-fp4-mi355x-sglang-disagg-agentic-umbp-dspark:
image: lmsysorg/sglang-rocm:v0.5.22-rocm720-mi35x-20261019
image: lmsysorg/sglang-rocm:v0.5.22-rocm10-mi35x-20261026
model: deepseek-ai/DeepSeek-V4-Pro-0813
model-prefix: dsv4
runner: cluster:mi355x-amds
Expand Down
9 changes: 9 additions & 0 deletions inferencex-e2e/perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11480,3 +11480,12 @@
- "Update the Muse Spark Open B300 curve to lmsysorg/sglang:nightly-dev-20261021-c1c287a4 and set SGLANG_FLASHINFER_NVFP4_PER_TOKEN_ACTIVATION=0 at every concurrency; run TP8/EP8 at concurrency 1, 4, 8, 10, 14, 16, 20, 24 and TP4/EP4 HiCache at concurrency 16, 28, 32, 40, 44, 48."
- "Use shortest-prefill-first at TP8 concurrency 10-24, stream interval 20 at TP8 concurrency 4, 20, 24 and TP4 concurrency 28-48, SGLANG_TRTLLM_MHA_DECODE_SEQ_LEN_SPLITS=4 at TP4 concurrency 40-48, and at concurrency 44 and 48 request admission 24 and 26 with FCFS, no prefill-decode interval, HiCache write_back and SWA/full ratio 0.1."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4417

- config-keys:
- dsv4-fp4-mi355x-sglang-disagg-agentic-umbp-dspark
scenario-type:
- agentic-coding
description:
- "Update the MI355X DeepSeek-V4-Pro-0813 SGLang MoRI disaggregated AgentX serving image from lmsysorg/sglang-rocm:v0.5.22-rocm720-mi35x-20261019 to lmsysorg/sglang-rocm:v0.5.22-rocm10-mi35x-20261026, the latest published MI35x ROCm 10 nightly (digest sha256:edabad83728ab04e3eae39f315eb16261eeb64dbdb051112bd22fc88560b60c4)."
- "Preserve all eight concurrency points (1, 16, 32, 48, 192, 256, 384, 512), prefill/decode topology, DSpark settings, UMBP offload, MoRI transfer, and benchmark client image. The workload binder supplies the serving image to every selected recipe variant."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4571
Loading