[AMD] Enable ROCm kvcache JIT path and add AMD CI coverage. (#18992)

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Hubert Lu
2026-02-24 22:15:05 -08:00
committed by GitHub
parent aff2f130ec
commit 8bd644765f
10 changed files with 168 additions and 12 deletions

View File

@@ -65,6 +65,7 @@ jobs:
outputs:
main_package: ${{ steps.filter.outputs.main_package || steps.run-mode.outputs.run_all_tests }}
sgl_kernel: ${{ steps.filter.outputs.sgl_kernel || steps.run-mode.outputs.run_all_tests }}
jit_kernel: ${{ steps.filter.outputs.jit_kernel || steps.run-mode.outputs.run_all_tests }}
multimodal_gen: ${{ steps.filter.outputs.multimodal_gen || steps.run-mode.outputs.run_all_tests }}
steps:
- name: Checkout code
@@ -102,6 +103,9 @@ jobs:
sgl_kernel:
- "sgl-kernel/**"
- ".github/workflows/pr-test-amd-rocm720.yml"
jit_kernel:
- "python/sglang/jit_kernel/**"
- ".github/workflows/pr-test-amd-rocm720.yml"
multimodal_gen:
- "python/sglang/multimodal_gen/**"
- "python/sglang/cli/**"
@@ -238,6 +242,45 @@ 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-amd --continue-on-error
jit-kernel-unit-test-amd:
needs: [check-changes]
if: |
always() &&
(
(inputs.target_stage == 'jit-kernel-unit-test-amd') ||
(
!inputs.target_stage &&
needs.check-changes.outputs.jit_kernel == 'true'
)
)
strategy:
fail-fast: false
matrix:
runner: [linux-mi325-gpu-1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Ensure VRAM is clear
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: |
bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
- name: Run JIT kernel unit tests
timeout-minutes: 10
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-small-1-gpu-amd:
needs: [check-changes]
if: |
@@ -756,6 +799,7 @@ jobs:
multimodal-gen-test-2-gpu-amd,
stage-a-test-1-amd,
jit-kernel-unit-test-amd,
stage-b-test-small-1-gpu-amd,
stage-b-test-small-1-gpu-amd-mi35x,
stage-b-test-large-1-gpu-amd,

View File

@@ -62,6 +62,7 @@ jobs:
outputs:
main_package: ${{ steps.filter.outputs.main_package || steps.run-mode.outputs.run_all_tests }}
sgl_kernel: ${{ steps.filter.outputs.sgl_kernel || steps.run-mode.outputs.run_all_tests }}
jit_kernel: ${{ steps.filter.outputs.jit_kernel || steps.run-mode.outputs.run_all_tests }}
multimodal_gen: ${{ steps.filter.outputs.multimodal_gen || steps.run-mode.outputs.run_all_tests }}
steps:
- name: Checkout code
@@ -99,6 +100,9 @@ jobs:
sgl_kernel:
- "sgl-kernel/**"
- ".github/workflows/pr-test-amd.yml"
jit_kernel:
- "python/sglang/jit_kernel/**"
- ".github/workflows/pr-test-amd.yml"
multimodal_gen:
- "python/sglang/multimodal_gen/**"
- "python/sglang/cli/**"
@@ -235,6 +239,45 @@ 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-amd
jit-kernel-unit-test-amd:
needs: [check-changes]
if: |
always() &&
(
(inputs.target_stage == 'jit-kernel-unit-test-amd') ||
(
!inputs.target_stage &&
needs.check-changes.outputs.jit_kernel == 'true'
)
)
strategy:
fail-fast: false
matrix:
runner: [linux-mi325-gpu-1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Ensure VRAM is clear
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: |
bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run JIT kernel unit tests
timeout-minutes: 10
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-small-1-gpu-amd:
needs: [check-changes, stage-a-test-1-amd]
if: |
@@ -845,6 +888,7 @@ jobs:
multimodal-gen-test-2-gpu-amd,
stage-a-test-1-amd,
jit-kernel-unit-test-amd,
stage-b-test-small-1-gpu-amd,
stage-b-test-small-1-gpu-amd-mi35x,
stage-b-test-large-1-gpu-amd,