Skip to content

[Klaud Cold] Update DeepSeek-V4-Pro FP4 MI355X vLLM AgentX MTP image to nightly-5d35ce39 / [Klaud Cold] 将 DeepSeek-V4-Pro FP4 MI355X vLLM AgentX MTP 镜像更新至 nightly-5d35ce39 #4578

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
Klaud-Cold wants to merge 2 commits into
base: main
Choose a base branch
from
Open

[Klaud Cold] Update DeepSeek-V4-Pro FP4 MI355X vLLM AgentX MTP image to nightly-5d35ce39 / [Klaud Cold] 将 DeepSeek-V4-Pro FP4 MI355X vLLM AgentX MTP 镜像更新至 nightly-5d35ce39 #4578

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7095711
chore(amd): update DSv4 FP4 MI355X vLLM AgentX MTP image to nightly-5…
github-actions[bot] Oct 27, 2026
29655ec
chore(amd): add perf-changelog entry for DSv4 FP4 MI355X vLLM AgentX …
github-actions[bot] Oct 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
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 @@ -988,7 +988,7 @@ qwen3.5-fp8-mi325x-sglang-mtp:
# DeepSeek-V4-Pro-0813 FP4 AgentX on one MI355X node using vLLM DSpark K6.
# Keep the historical config key for changelog compatibility.
dsv4-fp4-mi355x-vllm-agentic-mtp:
image: vllm/vllm-openai-rocm:nightly-e9757321527ca1ecd514c07c1418dd2c53da3d19
image: vllm/vllm-openai-rocm:nightly-5d35ce3934a7804b298559d2d99eec33792e1eb9@sha256:0c030ba9e2e5fd2f45f2a048a1c8bb239d9674b63297166b79e258b4ce65c6cc
model: deepseek-ai/DeepSeek-V4-Pro-0813
model-prefix: dsv4
runner: cluster:mi355x-amds
Expand Down
8 changes: 8 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 @@ -11413,3 +11413,11 @@
- Restore the MI355X MiniMax-M3 FP4 vLLM AgentX TP2/TP4 grid from run 34609443618 attempt 2 using SRT recipes. Update nightly-2a02f6efe319c885e3ccbcecde402e0028f9ec1e to nightly-df6603f0583375f244d1ac6d36265462b7490392 (2026-10-22, digest sha256:81899892d73777a4ae81e16f39e749169687f29249505eb4c56da83bd097d41c).
- Enable upstream MiniMax-M3 monokernel at TP4 with Model Runner V2, AITER MoE, FP8 KV/indexer and block size 128; keep TP2 on ordinary decode. Preserve EAGLE3-GQA with three draft tokens and use automatic golden acceptance for throughput with real verification for evals.
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4418

- config-keys:
- dsv4-fp4-mi355x-vllm-agentic-mtp
scenario-type:
- agentic-coding
description:
- Update the vLLM ROCm image from nightly-e9757321 to nightly-5d35ce39, pinned by digest.
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4578
Loading