Utils refactor (#1)

* fix(ci): recover from corrupted MMMU parquet cache (sgl-project#17256)

* [diffusion] feat: support default 4-step inference for Flux2-Klein distilled models (sgl-project#17225)

Signed-off-by: Lancer <maruixiang6688@gmail.com>

* Add runner utilization report workflow (sgl-project#17234)

* cli: support sglang version (sgl-project#17250)

* Use swa radix cache and memory pool for gpt-oss model (sgl-project#17261)

* [VLM][Reland] Refactor load_mm_data to improve performance (sgl-project#16152)

Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>

* [Tiny] Improve docs (sgl-project#17264)

* [diffusion] fix: set guidance_scale default to None (sgl-project#17182)

* Tiny fix comment typo (sgl-project#17287)

* [SPEC_V2] Enable cudagraph draft_extend for trtllm_mla_backend and Acclen Fix for DP under cudagraph mode (sgl-project#16974)

* Add kl test for swa radix cache (sgl-project#17281)

* fix: Handle multiple named chat templates in HuggingFace tokenizers (sgl-project#17236)

Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>

* Move radix cache related tests (sgl-project#17295)

* [Refactor] Add `-fp4-gemm-backend` to replace `SGLANG_FLASHINFER_FP4_GEMM_BACKEND` (sgl-project#16534)

Co-authored-by: Vincent Zhong <207368749+vincentzed@users.noreply.github.com>

* [Bugfix] Fix PD accuracy when MTP is not configured on the prefill node (sgl-project#17212)

Co-authored-by: Shangming Cai <csmthu@gmail.com>

* [Diffusion] Apply jit qk_norm to flux1 (sgl-project#17296)

* [Refactor] Split out deepseek v2 weight loader function into mixin (sgl-project#16649)

* [NPU]Support GPT-OSS for NPU (sgl-project#14197)

* [jit-kernel] Add CuTe DSL GDN Decode Kernel (sgl-project#15631)

Co-authored-by: Jinyan Chen <jinyanc@nvidia.com>

* [GLM 4.7] Add RTX 6000 Pro aka sm120 (sgl-project#17235)

Co-authored-by: root <root@ubuntu-nvidia.localdomain>

* Update CODEOWNERS for multimodal_gen (sgl-project#17308)

Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>

* [Feature] overlap LoRA weight loading with compute (sgl-project#15512)

* [PD] Optimize MHA models pp util calculation logic (sgl-project#17306)

* [Minor] Correct sglang version when installing from source (sgl-project#17315)

* Use dsv3 optimized routing `fused_topk_deepseek` instead of `moe_fused_gate` (sgl-project#15347)

* [DeepSeek v3.2] Opt MTP decode cuda batch sizes and nsa implementation (sgl-project#16961)

* Update code sync scripts (sgl-project#17319)

* [Auto Sync] Update tokenizer_manager.py (20260119) (sgl-project#17317)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* support new qwen3_coder_detector (sgl-project#16744)

Co-authored-by: liugaoji.lgj <liugaoji.lgj@alibaba-inc.com>

* Fix kernel selection in biased_grouped_topk_gpu (sgl-project#17325)

* KV Cache Events with Attention DP bug fix (sgl-project#16030) (sgl-project#16412)

* [Perf] fuse q, k norm for Flux2Attention (sgl-project#17241)

Co-authored-by: Minglei Zhu <zminglei@linkedin.com>

* [CI] Add partition to stage-b-test-large-1-gpu (11->12) (sgl-project#17245)

* fix(ci): rate limit and permission errors in trace publishing (sgl-project#17238)

* Revert "[Perf] fuse q, k norm for Flux2Attention (sgl-project#17241)" (sgl-project#17332)

* Migrate performance, accuracy, and quantization tests to CI registry (sgl-project#17177)

Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>

* Inclusion of nvfp4 blockscale in EPLB Rebalance (sgl-project#17158)

* [Refactor] Set `fp4-gemm-backend=auto` on SM100 and rename `fp4-gemm-backend` with `flashinfer_` prefix (sgl-project#17309)

* [Diffusion] Apply qknorm to flux2 and apply lightx2v rms_norm_one_pass kernel(without residual) (sgl-project#17305)

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* Fix v32 continue_final_message not work (sgl-project#16567)

* Evict swa kv cache during decoding (sgl-project#17220)

* [RadixTree][1/N Refactor]: Support unified match_prefix params (sgl-project#17142)

Co-authored-by: yizhang2077 <1109276519@qq.com>
Co-authored-by: pansicheng <sicheng.pan.chn@gmail.com>

* [AMD CI] Migrate and Add More Testcases (sgl-project#17116)

Co-authored-by: yctseng0211 <yctseng@amd.com>

* [AMD] CI - add partitions for stage-b-test-small-1-gpu-amd (sgl-project#17345)

* Restore deepseek_v2.py to main's code, except the utils

* Ran `pre-commit`

---------

Signed-off-by: Lancer <maruixiang6688@gmail.com>
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Hudson Xing <1277646412@qq.com>
Co-authored-by: Lancer <402430575@qq.com>
Co-authored-by: Alison Shao <54658187+alisonshao@users.noreply.github.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>
Co-authored-by: Yuan Luo <yuan.luo@hotmail.com>
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
Co-authored-by: Mohammad Miadh Angkad <mangkad.bsdsba2027@aim.edu>
Co-authored-by: Changyi Yang <112288487+ChangyiYang@users.noreply.github.com>
Co-authored-by: YAMY <74099316+YAMY1234@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: b8zhong <b8zhong@uwaterloo.ca>
Co-authored-by: Vincent Zhong <207368749+vincentzed@users.noreply.github.com>
Co-authored-by: Ch3ngY1 <91232537+Ch3ngY1@users.noreply.github.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
Co-authored-by: Jerry Ji <jerryjilol@gmail.com>
Co-authored-by: Todobe <43903496+Todobe@users.noreply.github.com>
Co-authored-by: Jinyan Chen <93358689+liz-badada@users.noreply.github.com>
Co-authored-by: Jinyan Chen <jinyanc@nvidia.com>
Co-authored-by: Koushik Dutta <koush@koushikdutta.com>
Co-authored-by: root <root@ubuntu-nvidia.localdomain>
Co-authored-by: Glen Liu <62917497+glenliu21@users.noreply.github.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Lee Nau <lnau@nvidia.com>
Co-authored-by: Yongfei Xu <xuyongfei.xyf@antgroup.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Gaoji Liu <34803073+attack204@users.noreply.github.com>
Co-authored-by: liugaoji.lgj <liugaoji.lgj@alibaba-inc.com>
Co-authored-by: yudian0504 <138860534+yudian0504@users.noreply.github.com>
Co-authored-by: Kartik Ramesh <kartikx2000@gmail.com>
Co-authored-by: Minglei Zhu <mingleizhu1122@gmail.com>
Co-authored-by: Minglei Zhu <zminglei@linkedin.com>
Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>
Co-authored-by: Shu Wang <shuw@nvidia.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: ybyang <10629930+whybeyoung@users.noreply.github.com>
Co-authored-by: zhangheng <hzh0425@apache.org>
Co-authored-by: yizhang2077 <1109276519@qq.com>
Co-authored-by: pansicheng <sicheng.pan.chn@gmail.com>
Co-authored-by: Bingxu Chen <Bingxu.Chen@amd.com>
Co-authored-by: yctseng0211 <yctseng@amd.com>

Author: 44 people

.github/CODEOWNERS

@@ -4,6 +4,8 @@
 /python/pyproject.toml @merrymercy @Fridge003 @ispobock
 /python/sglang/jit_kernel @DarkSharpness @BBuf
 /python/sglang/multimodal_gen @mickqian @yhyang201
+/python/sglang/multimodal_gen/runtime/layers @mickqian @yhyang201 @BBuf
+/python/sglang/multimodal_gen/runtime/models/dits @mickqian @yhyang201 @BBuf
 /python/sglang/srt/batch_invariant_ops @Fridge003 @hebiao064
 /python/sglang/srt/constrained @hnyls2002 @DarkSharpness
 /python/sglang/srt/compilation @hebiao064

.github/workflows/open-pr-copy-from-oss.yml

@@ -23,6 +23,6 @@ jobs:
 
       - name: Copy from OSS code
         env:
-          GH_TOKEN: ${{ secrets.PAT_FOR_CODE_SYNC_FROM_LIANMIN }}
+          GH_TOKEN: ${{ secrets.GH_PAT_FOR_OPEN_PR_TO_PRIVATE }}
         run: |
           python3 scripts/code_sync/copy_from_oss.py

.github/workflows/open-pr-copy-to-oss.yml

@@ -26,6 +26,6 @@ jobs:
 
       - name: Copy to OSS code
         env:
-          GH_TOKEN: ${{ secrets.PAT_FOR_CODE_SYNC_FROM_LIANMIN }}
+          GH_TOKEN: ${{ secrets.GH_PAT_FOR_OPEN_PR_TO_OSS }}
         run: |
           python3 scripts/code_sync/copy_to_oss.py --commit ${{ github.event.inputs.commit_sha }}

.github/workflows/pr-test-amd.yml

@@ -149,7 +149,10 @@ jobs:
           docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_topk.py
           docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_kvcacheio.py
           docker exec -w /sglang-checkout/sgl-kernel/tests/sgl_diffusion ci_sglang python3 -m pytest test_timestep_embedding.py
-
+          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
+          docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_amd_deterministic_custom_allreduce.py
+          docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_amd_nccl_allreduce_determinism.py
   # =============================================== primary ====================================================
 
   stage-a-test-1-amd:
@@ -190,7 +193,7 @@ jobs:
       - name: Run test
         timeout-minutes: 10
         run: |
-          bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1
+          bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1-amd
 
   stage-b-test-small-1-gpu-amd:
     needs: [check-changes, stage-a-test-1-amd]
@@ -208,7 +211,7 @@ jobs:
       fail-fast: false
       matrix:
         runner: [linux-mi325-gpu-1]
-        part: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+        part: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
     runs-on: ${{matrix.runner}}
     steps:
       - name: Checkout code
@@ -230,7 +233,7 @@ jobs:
       - name: Run test
         timeout-minutes: 30
         run: |
-          bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 12 --timeout-per-file 1800
+          bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 13 --timeout-per-file 1800
 
   stage-b-test-small-1-gpu-amd-mi35x:
     needs: [check-changes, stage-a-test-1-amd]
@@ -548,52 +551,13 @@ jobs:
           echo "=== Post-test System Memory Status ==="
           free -h
 
-  unit-test-backend-1-gpu-amd:
-    needs: [check-changes, stage-a-test-1-amd]
-    if: |
-      always() &&
-      (
-        (inputs.target_stage == 'unit-test-backend-1-gpu-amd') ||
-        (
-          !inputs.target_stage &&
-          (!failure() && !cancelled()) &&
-          ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
-        )
-      )
-    strategy:
-      fail-fast: false
-      matrix:
-        runner: [linux-mi325-gpu-1]
-        part: [0, 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_ci_start_container.sh
-        env:
-          GITHUB_WORKSPACE: ${{ github.workspace }}
-
-      - name: Install dependencies
-        run: bash scripts/ci/amd_ci_install_dependency.sh
 
-      - name: Run test
-        timeout-minutes: 30
-        run: |
-          bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
-
-  unit-test-backend-8-gpu-amd:
-    needs: [check-changes, stage-a-test-1-amd]
+  stage-c-test-large-8-gpu-amd:
+    needs: [check-changes, call-gate, stage-b-test-small-1-gpu-amd, stage-b-test-large-2-gpu-amd]
     if: |
       always() &&
       (
-        (inputs.target_stage == 'unit-test-backend-8-gpu-amd') ||
+        (inputs.target_stage == 'stage-c-test-large-8-gpu-amd') ||
         (
           !inputs.target_stage &&
           (!failure() && !cancelled()) &&
@@ -634,7 +598,7 @@ jobs:
       - name: Run test
         timeout-minutes: 60
         run: |
-          bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-8-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 3600
+          bash scripts/ci/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 2 --timeout-per-file 3600
 
   stage-c-test-large-8-gpu-amd-mi35x:
     needs: [check-changes, call-gate, stage-b-test-small-1-gpu-amd, stage-b-test-large-2-gpu-amd]
@@ -713,23 +677,29 @@ jobs:
       - name: Benchmark single latency
         timeout-minutes: 20
         run: |
-          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_small
-          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_default
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_one_batch_1gpu.TestBenchOneBatch1GPU.test_bs1_small
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_one_batch_1gpu.TestBenchOneBatch1GPU.test_bs1_default
 
       - name: Benchmark online latency
         timeout-minutes: 15
         run: |
-          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_online_latency_default
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part1.TestBenchServing1GPUPart1.test_online_latency_default
+
+      - name: Benchmark online latency (LoRA)
+        timeout-minutes: 10
+        run: |
+          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_lora_online_latency
+          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_lora_online_latency_with_concurrent_adapter_updates
 
       - name: Benchmark offline throughput
         timeout-minutes: 15
         run: |
-          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part1.TestBenchServing1GPUPart1.test_offline_throughput_default
 
       - name: Benchmark offline throughput (Non-streaming, small batch size)
         timeout-minutes: 15
         run: |
-          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_non_stream_small_batch_size
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part1.TestBenchServing1GPUPart1.test_offline_throughput_non_stream_small_batch_size
 
   performance-test-1-gpu-part-2-amd:
     needs: [check-changes, stage-a-test-1-amd]
@@ -768,17 +738,81 @@ jobs:
       - name: Benchmark offline throughput (w/o RadixAttention)
         timeout-minutes: 15
         run: |
-          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_without_radix_cache
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part1.TestBenchServing1GPUPart1.test_offline_throughput_without_radix_cache
 
       - name: Benchmark offline throughput (w/ Triton)
         timeout-minutes: 15
         run: |
-          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_with_triton_attention_backend
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part1.TestBenchServing1GPUPart1.test_offline_throughput_with_triton_attention_backend
 
       - name: Benchmark offline throughput (w/ FP8)
         timeout-minutes: 15
         run: |
-          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default_fp8
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_large.TestBenchServing1GPULarge.test_offline_throughput_default_fp8
+
+      - name: Benchmark VLM offline throughput
+        timeout-minutes: 10
+        run: |
+          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_vlm_offline_throughput
+
+      - name: Benchmark VLM online latency
+        timeout-minutes: 10
+        run: |
+          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_vlm_online_latency
+
+  performance-test-1-gpu-part-3-amd:
+    needs: [check-changes, stage-a-test-1-amd]
+    if: |
+      always() &&
+      (
+        (inputs.target_stage == 'performance-test-1-gpu-part-3-amd') ||
+        (
+          !inputs.target_stage &&
+          (!failure() && !cancelled()) &&
+          ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_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_ci_start_container.sh
+        env:
+          GITHUB_WORKSPACE: ${{ github.workspace }}
+
+      - name: Install dependencies
+        run: bash scripts/ci/amd_ci_install_dependency.sh
+
+      - name: Benchmark Scores online latency and throughput
+        timeout-minutes: 10
+        run: |
+          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_score_api_latency_throughput
+
+      - name: Benchmark Scores online latency and throughput (batch size scaling)
+        timeout-minutes: 10
+        run: |
+          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_score_api_batch_scaling
+
+      - name: Benchmark Embeddings online latency and throughput
+        timeout-minutes: 10
+        run: |
+          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_embeddings_api_latency_throughput
+
+      - name: Benchmark Embeddings online latency and throughput (batch size scaling)
+        timeout-minutes: 10
+        run: |
+          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_embeddings_api_batch_scaling
 
   performance-test-2-gpu-amd:
     needs: [check-changes, stage-a-test-1-amd]
@@ -822,32 +856,32 @@ jobs:
       - name: Benchmark single latency (TP=2)
         timeout-minutes: 25
         run: |
-          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_moe_tp2_bs1
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_one_batch_2gpu.TestBenchOneBatch2GPU.test_moe_tp2_bs1
 
       - name: Benchmark single latency + torch.compile (TP=2)
         timeout-minutes: 25
         run: |
-          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_torch_compile_tp2_bs1
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_one_batch_2gpu.TestBenchOneBatch2GPU.test_torch_compile_tp2_bs1
 
       - name: Benchmark offline throughput (TP=2)
         timeout-minutes: 25
         run: |
-          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_default
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_2gpu.TestBenchServing2GPU.test_moe_offline_throughput_default
 
       - name: Benchmark offline throughput (w/o RadixAttention) (TP=2)
         timeout-minutes: 25
         run: |
-          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_without_radix_cache
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_2gpu.TestBenchServing2GPU.test_moe_offline_throughput_without_radix_cache
 
       - name: Benchmark offline PP decode throughput (PP=2)
         timeout-minutes: 10
         run: |
-          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_pp_offline_throughput_default_decode
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_2gpu.TestBenchServing2GPU.test_pp_offline_throughput_default_decode
 
       - name: Benchmark offline PP prefill throughput (PP=2)
         timeout-minutes: 10
         run: |
-          bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_pp_long_context_prefill
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_2gpu.TestBenchServing2GPU.test_pp_long_context_prefill
 
   accuracy-test-1-gpu-amd:
     needs: [check-changes, stage-a-test-1-amd]
@@ -886,7 +920,7 @@ jobs:
       - name: Evaluate Accuracy
         timeout-minutes: 30
         run: |
-          bash scripts/ci/amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_eval_accuracy_large.py
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/eval -e SGLANG_USE_AITER=0 python3 test_eval_accuracy_large.py
 
   accuracy-test-2-gpu-amd:
     needs: [check-changes, accuracy-test-1-gpu-amd]
@@ -926,7 +960,7 @@ jobs:
       - name: Evaluate accuracy (TP=2)
         timeout-minutes: 30
         run: |
-          bash scripts/ci/amd_ci_exec.sh -e SGLANG_USE_AITER_AR=0 -e SGLANG_USE_AITER=0 -e HF_HUB_ENABLE_HF_TRANSFER=0 python3 test_moe_eval_accuracy_large.py
+          bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/eval -e SGLANG_USE_AITER_AR=0 -e SGLANG_USE_AITER=0 -e HF_HUB_ENABLE_HF_TRANSFER=0 python3 test_moe_eval_accuracy_large.py
 
   pr-test-amd-finish:
     needs:
@@ -942,11 +976,11 @@ jobs:
         stage-b-test-small-1-gpu-amd,
         stage-b-test-small-1-gpu-amd-mi35x,
         stage-b-test-large-2-gpu-amd,
-        unit-test-backend-1-gpu-amd,
-        unit-test-backend-8-gpu-amd,
+        stage-c-test-large-8-gpu-amd,
         stage-c-test-large-8-gpu-amd-mi35x,
         performance-test-1-gpu-part-1-amd,
         performance-test-1-gpu-part-2-amd,
+        performance-test-1-gpu-part-3-amd,
         performance-test-2-gpu-amd,
         accuracy-test-1-gpu-amd,
         accuracy-test-2-gpu-amd,