Skip to content

[AMD][MI35X] Bump qwen3.5-mxfp4 MI355X SGLang single-node image to v0.5.16 #2433

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

Open
yichiche wants to merge 9 commits into
base: main
Choose a base branch
from
+10 −4
Open

[AMD][MI35X] Bump qwen3.5-mxfp4 MI355X SGLang single-node image to v0.5.16 #2433

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
c9dbedd
[AMD][MI35X] Bump qwen3.5-mxfp4 MI355X SGLang single-node image to v0…
yichiche Jul 31, 2026
760e7d3
[AMD][MI35X] Point qwen3.5-mxfp4 changelog entry to PR #2433
yichiche Jul 31, 2026
8eb57da
[AMD][MI35X] Sync perf-changelog with main and re-append qwen3.5-mxfp…
yichiche Aug 4, 2026
f952893
Merge branch 'main' into amd/qwen3.5-fp4-mi355x-sglang-v0.5.16
yichiche Aug 4, 2026
b9be46d
Merge branch 'main' into amd/qwen3.5-fp4-mi355x-sglang-v0.5.16
yichiche Aug 4, 2026
72d62d5
[AMD][MI35X] Add trailing newline to perf-changelog.yaml
yichiche Aug 4, 2026
8146dc5
Merge branch 'main' into amd/qwen3.5-fp4-mi355x-sglang-v0.5.16
yichiche Aug 5, 2026
6511b87
Merge branch 'main' into amd/qwen3.5-fp4-mi355x-sglang-v0.5.16
yichiche Aug 6, 2026
1f73b4f
[AMD][MI35X] Add trailing newline to perf-changelog.yaml
yichiche Aug 6, 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
4 changes: 2 additions & 2 deletions configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -306,7 +306,7 @@ qwen3.5-fp8-mi355x-sglang-disagg:
- "DECODE_MTP_SIZE=0"

qwen3.5-fp4-mi355x-sglang:
image: lmsysorg/sglang-rocm:v0.5.15-rocm720-mi35x-20260713
image: lmsysorg/sglang-rocm:v0.5.16-rocm720-mi35x-20260730
model: amd/Qwen3.5-397B-A17B-MXFP4
model-prefix: qwen3.5
runner: mi355x
Expand Down Expand Up @@ -338,7 +338,7 @@ qwen3.5-fp4-mi355x-atom:
- { tp: 4, conc-start: 4, conc-end: 16 }

qwen3.5-fp4-mi355x-sglang-mtp:
image: lmsysorg/sglang-rocm:v0.5.15-rocm720-mi35x-20260713
image: lmsysorg/sglang-rocm:v0.5.16-rocm720-mi35x-20260730
model: amd/Qwen3.5-397B-A17B-MXFP4
model-prefix: qwen3.5
runner: mi355x
Expand Down
10 changes: 8 additions & 2 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5403,7 +5403,7 @@
- "Bump vLLM nightly image to nightly-5e35a6f4f9bbc217c599692157ca985c894373f7 (fixed-len MiniMax-M3 fix); update 2p1d-dep2-dep4 recipe YAML container to match"
- "Enable minimax_m3_msa_decode_backend=cutlass in decode attention-config"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2483

- config-keys:
- minimaxm3-fp4-b300-vllm
description:
Expand Down Expand Up @@ -5449,7 +5449,7 @@
- "Enable prefill-only INT4 quick-reduce: set VLLM_ROCM_QUICK_REDUCE_QUANTIZATION=INT4 and VLLM_ROCM_QUICK_REDUCE_MAX_SIZE_BYTES_MB=2048 on the prefill workers via a new prefill_env channel (mirrors the existing decode_env path in server_vllm.sh)."
- "Cap the 1P1D TP4 concurrency sweep at 256 (was 512); drop the 2P1D TP4 layout (128/256/512) as it is CI-flaky with negligible curve impact."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1943

- config-keys:
- minimaxm3-fp4-b300-vllm-agentic-mtp
scenario-type:
Expand All @@ -5460,3 +5460,9 @@
- "Use vllm/vllm-openai:nightly-387189c42997b27e2c04b5d97ef8190ffa2bf909 with prefix caching enabled, default KV-cache dtype, FlashInfer TRT-LLM attention with FP8 indexer KV, and the EAGLE3 drafter on FLASH_ATTN."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2328

- config-keys:
- qwen3.5-fp4-mi355x-sglang
- qwen3.5-fp4-mi355x-sglang-mtp
description:
- "Bump image from lmsysorg/sglang-rocm:v0.5.15-rocm720-mi35x-20260713 to lmsysorg/sglang-rocm:v0.5.16-rocm720-mi35x-20260730"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2433