cookbook(qwen3.5): add MI355X disaggregated inference and MTP commands, bump image to v0.5.16 - #34413
Closed
ChangLiu0709 wants to merge 2 commits into
Closed
ChangLiu0709 wants to merge 2 commits into
ChangLiu0709 wants to merge 2 commits into
Conversation
…to v0.5.16 - Bump AMD MI355X docker image from v0.5.15.post1-rocm720-mi35x-20260715 to lmsysorg/sglang:v0.5.16-rocm720-mi35x - Add disaggregated inference (MoRI 1P1D) deployment commands for MI355X: TP4 prefill + TP8 decode (12 GPUs), which delivers 24-31% better throughput/GPU vs TP8P+TP8D (16 GPUs) with identical interactivity - Add DI + MTP (EAGLE speculative decoding) deployment commands: EAGLE depth 3 on TP4P+TP8D, with guidance to switch decode to TP4 at conc≥128 to avoid MTP throughput collapse Aligns with InferenceX PR SemiAnalysisAI/InferenceX#2557. Co-authored-by: Cursor <cursoragent@cursor.com>
ChangLiu0709
requested review from
JustinTong0323,
sogalin,
wisclmy0611 and
zijiexia
as code owners
August 11, 2026 11:43
github-actions
Bot
added
the
documentation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Motivation
Add disaggregated inference (DI) and MTP (EAGLE speculative decoding) deployment commands for Qwen3.5-FP8 on AMD MI355X to the cookbook page, and bump the MI355X docker image to v0.5.16.
This aligns with InferenceX PR SemiAnalysisAI/InferenceX#2557 which adds the corresponding benchmark configurations.
Changes
docs/cookbook/autoregressive/Qwen/Qwen3.5.mdx:lmsysorg/sglang-rocm:v0.5.15.post1-rocm720-mi35x-20260715→lmsysorg/sglang:v0.5.16-rocm720-mi35xNotes
--disaggregation-mode prefill/decodeand--disaggregation-transfer-backend mori.cc @zijiexia @yichiche
Made with Cursor
CI States
Latest PR Test (Base): ✅ Run #31708425253
Latest PR Test (Extra): ❌ Run #31708424884