[AMD][DeepSeek V4] Set SGLANG_OPT_FLASHMLA_SPARSE_PREFILL to false on hip code path - #30237
Conversation
There was a problem hiding this comment.
Code Review
This pull request modifies the DeepSeek-V4 hook for ROCm/HIP platforms by removing the check for whether the SGLANG_OPT_FLASHMLA_SPARSE_PREFILL environment variable is set. This change unconditionally disables the sparse prefill kernel on ROCm/HIP, preventing users from explicitly overriding this behavior. The reviewer recommends restoring the check to allow explicit overrides as documented in the warning message.
Important
The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.
|
Post-merge validation note (full DSV4-Flash disagg matrix on image Run: https://github.com/sgl-project/sglang/actions/runs/28817206537 This PR does what it intends — every prefill + decode log across all 8 flash configs shows However, DeepSeek-V4-Flash disagg is still failing, and with sparse prefill confirmed disabled the cause is now clearly a separate MORI/RDMA transport issue, not the sparse path: This is uniform across all 8 flash configs (fp8/fp4 × base/mtp/dp8ep8/dp8ep8-mtp), so it's systematic — a ~6.8 GB RDMA memory-region registration failing with Net: #30237 correctly disables sparse prefill on HIP, but does not by itself green the Flash disagg nightly because of this RDMA registration failure. |
co-authored: @bingxche, @michaelzhang-ai
Motivation
Modifications
Accuracy Tests
Speed Tests and Profiling
Checklist
Review and Merge Process
/tag-and-rerun-ci,/tag-run-ci-label,/rerun-failed-ciCI States
Latest PR Test (Base): ❌ Run #28777920839
Latest PR Test (Extra): ❌ Run #28777920522