diff --git a/.github/workflows/pr-test-amd-rocm720.yml b/.github/workflows/pr-test-amd-rocm720.yml index 781d7e28f..b34b61105 100644 --- a/.github/workflows/pr-test-amd-rocm720.yml +++ b/.github/workflows/pr-test-amd-rocm720.yml @@ -33,21 +33,21 @@ on: default: '' options: - '' - - sgl-kernel-unit-test-amd - - sgl-kernel-unit-test-2-gpu-amd - - stage-a-test-1-gpu-small-amd - - jit-kernel-unit-test-amd - - stage-b-test-1-gpu-small-amd - - stage-b-test-1-gpu-small-amd-nondeterministic - - stage-b-test-1-gpu-small-amd-mi35x - - stage-b-test-1-gpu-large-amd - - stage-b-test-2-gpu-large-amd - - multimodal-gen-test-1-gpu-amd - - multimodal-gen-test-2-gpu-amd - - stage-c-test-large-8-gpu-amd - - stage-c-test-large-8-gpu-amd-mi35x - - stage-b-test-large-8-gpu-disaggregation-amd - - stage-c-test-4-gpu-amd + - sgl-kernel-unit-test-amd-rocm720 + - sgl-kernel-unit-test-2-gpu-amd-rocm720 + - stage-a-test-1-gpu-small-amd-rocm720 + - jit-kernel-unit-test-amd-rocm720 + - stage-b-test-1-gpu-small-amd-rocm720 + - stage-b-test-1-gpu-small-amd-nondeterministic-rocm720 + - stage-b-test-1-gpu-small-amd-mi35x-rocm720 + - stage-b-test-1-gpu-large-amd-rocm720 + - stage-b-test-2-gpu-large-amd-rocm720 + - multimodal-gen-test-1-gpu-amd-rocm720 + - multimodal-gen-test-2-gpu-amd-rocm720 + - stage-c-test-large-8-gpu-amd-rocm720 + - stage-c-test-large-8-gpu-amd-mi35x-rocm720 + - stage-b-test-large-8-gpu-disaggregation-amd-rocm720 + - stage-c-test-4-gpu-amd-rocm720 target_stage: description: "Or type comma-separated stage names (overrides dropdown if non-empty)" required: false @@ -162,12 +162,12 @@ jobs: - "python/pyproject_other.toml" # =============================================== sgl-kernel ==================================================== - sgl-kernel-unit-test-amd: + sgl-kernel-unit-test-amd-rocm720: needs: [check-changes] if: | always() && ( - (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',sgl-kernel-unit-test-amd,')) || + (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',sgl-kernel-unit-test-amd-rocm720,')) || ( !(inputs.target_stage || inputs.target_stage_select) && needs.check-changes.outputs.sgl_kernel == 'true' @@ -208,12 +208,12 @@ jobs: docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_moe_topk_sigmoid.py docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_torch_defaults_reset.py - sgl-kernel-unit-test-2-gpu-amd: + sgl-kernel-unit-test-2-gpu-amd-rocm720: needs: [check-changes] if: | always() && ( - (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',sgl-kernel-unit-test-2-gpu-amd,')) || + (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',sgl-kernel-unit-test-2-gpu-amd-rocm720,')) || ( !(inputs.target_stage || inputs.target_stage_select) && needs.check-changes.outputs.sgl_kernel == 'true' @@ -249,12 +249,12 @@ jobs: # =============================================== primary ==================================================== - stage-a-test-1-gpu-small-amd: + stage-a-test-1-gpu-small-amd-rocm720: needs: [check-changes] if: | always() && ( - (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-a-test-1-gpu-small-amd,')) || + (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-a-test-1-gpu-small-amd-rocm720,')) || ( !(inputs.target_stage || inputs.target_stage_select) && (!failure() && !cancelled()) && @@ -288,12 +288,12 @@ jobs: run: | bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1-gpu-small-amd ${{ inputs.continue_on_error && '--continue-on-error' || '' }} - jit-kernel-unit-test-amd: + jit-kernel-unit-test-amd-rocm720: needs: [check-changes] if: | always() && ( - (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',jit-kernel-unit-test-amd,')) || + (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',jit-kernel-unit-test-amd-rocm720,')) || ( !(inputs.target_stage || inputs.target_stage_select) && needs.check-changes.outputs.jit_kernel == 'true' @@ -326,12 +326,12 @@ jobs: run: | bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout" python3 -m pytest -q python/sglang/jit_kernel/tests/test_store_cache.py - stage-b-test-1-gpu-small-amd: + stage-b-test-1-gpu-small-amd-rocm720: needs: [check-changes] if: | always() && ( - (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-small-amd,')) || + (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-small-amd-rocm720,')) || ( !(inputs.target_stage || inputs.target_stage_select) && (!failure() && !cancelled()) && @@ -365,12 +365,12 @@ jobs: run: | bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-1-gpu-small-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 14 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} - stage-b-test-1-gpu-small-amd-nondeterministic: + stage-b-test-1-gpu-small-amd-nondeterministic-rocm720: needs: [check-changes] if: | always() && ( - (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-small-amd-nondeterministic,')) || + (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-small-amd-nondeterministic-rocm720,')) || ( !(inputs.target_stage || inputs.target_stage_select) && (!failure() && !cancelled()) && @@ -403,12 +403,12 @@ jobs: run: | bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-1-gpu-small-amd-nondeterministic --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} - stage-b-test-1-gpu-small-amd-mi35x: + stage-b-test-1-gpu-small-amd-mi35x-rocm720: needs: [check-changes] if: | always() && ( - (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-small-amd-mi35x,')) || + (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-small-amd-mi35x-rocm720,')) || ( !(inputs.target_stage || inputs.target_stage_select) && (!failure() && !cancelled()) && @@ -441,12 +441,12 @@ jobs: run: | bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-1-gpu-small-amd-mi35x ${{ inputs.continue_on_error && '--continue-on-error' || '' }} - stage-b-test-1-gpu-large-amd: + stage-b-test-1-gpu-large-amd-rocm720: needs: [check-changes] if: | always() && ( - (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-large-amd,')) || + (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-large-amd-rocm720,')) || ( !(inputs.target_stage || inputs.target_stage_select) && (!failure() && !cancelled()) && @@ -480,12 +480,12 @@ jobs: run: | bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-1-gpu-large-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} - stage-b-test-2-gpu-large-amd: + stage-b-test-2-gpu-large-amd-rocm720: needs: [check-changes] if: | always() && ( - (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-2-gpu-large-amd,')) || + (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-2-gpu-large-amd-rocm720,')) || ( !(inputs.target_stage || inputs.target_stage_select) && (!failure() && !cancelled()) && @@ -519,12 +519,12 @@ jobs: run: | bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-2-gpu-large-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} - multimodal-gen-test-1-gpu-amd: + multimodal-gen-test-1-gpu-amd-rocm720: needs: [check-changes] if: | always() && ( - (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',multimodal-gen-test-1-gpu-amd,')) || + (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',multimodal-gen-test-1-gpu-amd-rocm720,')) || ( !(inputs.target_stage || inputs.target_stage_select) && (!failure() && !cancelled()) && @@ -650,12 +650,12 @@ jobs: echo "=== Post-test System Memory Status ===" free -h - multimodal-gen-test-2-gpu-amd: + multimodal-gen-test-2-gpu-amd-rocm720: needs: [check-changes] if: | always() && ( - (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',multimodal-gen-test-2-gpu-amd,')) || + (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',multimodal-gen-test-2-gpu-amd-rocm720,')) || ( !(inputs.target_stage || inputs.target_stage_select) && (!failure() && !cancelled()) && @@ -780,12 +780,12 @@ jobs: free -h - stage-c-test-4-gpu-amd: - needs: [check-changes, stage-b-test-1-gpu-small-amd, stage-b-test-2-gpu-large-amd] + stage-c-test-4-gpu-amd-rocm720: + needs: [check-changes, stage-b-test-1-gpu-small-amd-rocm720, stage-b-test-2-gpu-large-amd-rocm720] if: | always() && ( - (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-c-test-4-gpu-amd,')) || + (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-c-test-4-gpu-amd-rocm720,')) || ( !(inputs.target_stage || inputs.target_stage_select) && (!failure() && !cancelled()) && @@ -836,12 +836,12 @@ jobs: --retry-timeout-increase 0 \ ${{ inputs.continue_on_error && '--continue-on-error' || '' }} - stage-c-test-large-8-gpu-amd: + stage-c-test-large-8-gpu-amd-rocm720: needs: [check-changes] if: | always() && ( - (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-c-test-large-8-gpu-amd,')) || + (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-c-test-large-8-gpu-amd-rocm720,')) || ( !(inputs.target_stage || inputs.target_stage_select) && (!failure() && !cancelled()) && @@ -883,12 +883,12 @@ jobs: 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 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} - stage-c-test-large-8-gpu-amd-mi35x: + stage-c-test-large-8-gpu-amd-mi35x-rocm720: needs: [check-changes] if: | always() && ( - (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-c-test-large-8-gpu-amd-mi35x,')) || + (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-c-test-large-8-gpu-amd-mi35x-rocm720,')) || ( !(inputs.target_stage || inputs.target_stage_select) && (!failure() && !cancelled()) && @@ -923,12 +923,12 @@ jobs: 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 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} # =============================================== Disaggregation ==================================================== - stage-b-test-large-8-gpu-35x-disaggregation-amd: + stage-b-test-large-8-gpu-35x-disaggregation-amd-rocm720: needs: [check-changes] if: | always() && ( - (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-large-8-gpu-disaggregation-amd,')) || + (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-large-8-gpu-disaggregation-amd-rocm720,')) || ( !(inputs.target_stage || inputs.target_stage_select) && (!failure() && !cancelled()) && @@ -1034,28 +1034,28 @@ jobs: -e SGLANG_TEST_RDMA_DEVICE="${{ env.SGLANG_TEST_RDMA_DEVICE }}" \ -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-8-gpu-35x-disaggregation-amd --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} - pr-test-amd-finish: + pr-test-amd-rocm720-finish: needs: [ call-gate, check-changes, - sgl-kernel-unit-test-amd, - sgl-kernel-unit-test-2-gpu-amd, - multimodal-gen-test-1-gpu-amd, - multimodal-gen-test-2-gpu-amd, + sgl-kernel-unit-test-amd-rocm720, + sgl-kernel-unit-test-2-gpu-amd-rocm720, + multimodal-gen-test-1-gpu-amd-rocm720, + multimodal-gen-test-2-gpu-amd-rocm720, - stage-a-test-1-gpu-small-amd, - jit-kernel-unit-test-amd, - stage-b-test-1-gpu-small-amd, - stage-b-test-1-gpu-small-amd-nondeterministic, - stage-b-test-1-gpu-small-amd-mi35x, - stage-b-test-1-gpu-large-amd, - stage-b-test-2-gpu-large-amd, - stage-b-test-large-8-gpu-35x-disaggregation-amd, - stage-c-test-4-gpu-amd, - stage-c-test-large-8-gpu-amd, - stage-c-test-large-8-gpu-amd-mi35x, + stage-a-test-1-gpu-small-amd-rocm720, + jit-kernel-unit-test-amd-rocm720, + stage-b-test-1-gpu-small-amd-rocm720, + stage-b-test-1-gpu-small-amd-nondeterministic-rocm720, + stage-b-test-1-gpu-small-amd-mi35x-rocm720, + stage-b-test-1-gpu-large-amd-rocm720, + stage-b-test-2-gpu-large-amd-rocm720, + stage-b-test-large-8-gpu-35x-disaggregation-amd-rocm720, + stage-c-test-4-gpu-amd-rocm720, + stage-c-test-large-8-gpu-amd-rocm720, + stage-c-test-large-8-gpu-amd-mi35x-rocm720, ] if: always() runs-on: ubuntu-latest diff --git a/.github/workflows/release-docker-amd-nightly.yml b/.github/workflows/release-docker-amd-nightly.yml index 616f2b9fe..dc8087b0a 100644 --- a/.github/workflows/release-docker-amd-nightly.yml +++ b/.github/workflows/release-docker-amd-nightly.yml @@ -1,4 +1,4 @@ -name: Release Docker Images Nightly (AMD) +name: Release Docker Images Nightly ROCm7.0 (AMD) on: workflow_dispatch: schedule: diff --git a/.github/workflows/release-docker-amd-rocm720-nightly.yml b/.github/workflows/release-docker-amd-rocm720-nightly.yml index 8686550e1..762689714 100644 --- a/.github/workflows/release-docker-amd-rocm720-nightly.yml +++ b/.github/workflows/release-docker-amd-rocm720-nightly.yml @@ -1,4 +1,4 @@ -name: Release Docker Images ROCm 7.2.0 Nightly Preview (AMD) +name: Release Docker Images Nightly ROCm7.2 (AMD) on: workflow_dispatch: schedule: