minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

[AMD] Add fused all-reduce RMSNorm per-group quant for Qwen3.5 FP8 (#24651)

Browse Source 
Co-authored-by: jacky.cheng <yichiche@amd.com>
Co-authored-by: yctseng0211 <yctseng@amd.com>
Co-authored-by: HAI <hixiao@gmail.com>
This commit is contained in:
Hubert Lu
2026-07-22 07:33:03 -07:00
committed by GitHub
co-authored by jacky.cheng yctseng0211 HAI
parent b855efd9e6
commit e8e765b9d6
9 changed files with 1192 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/pr-test-amd-rocm720.yml
+2 -2
View File
@@ -1080,7 +1080,7 @@ jobs:
fail-fast: false
matrix:
runner: [linux-mi35x-gpu-8]
part: [0, 1]
part: [0, 1, 2]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
@@ -1101,7 +1101,7 @@ jobs:
- name: Run test
timeout-minutes: 60
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 3600 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 3600 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
# =============================================== Disaggregation ====================================================
stage-b-test-large-8-gpu-mi35x-disaggregation-amd-rocm720:
.github/workflows/pr-test-amd.yml
+2 -2
View File
@@ -1135,7 +1135,7 @@ jobs:
fail-fast: false
matrix:
runner: [linux-mi35x-gpu-8]
part: [0, 1]
part: [0, 1, 2]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
@@ -1157,7 +1157,7 @@ jobs:
- name: Run test
timeout-minutes: 60
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 3600 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 3600 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
# =============================================== Disaggregation ====================================================
stage-b-test-large-8-gpu-mi35x-disaggregation-amd: