Commit 1744c6bde for llama.cpp

commit 1744c6bde8d687ce9774b3b54e688eee0bfdf5b7
Author: Daniel Bevenius <daniel.bevenius@gmail.com>
Date:   Tue Sep 8 13:36:03 2026 +0200

    ci : add PYTEST_WORKERS=1 to fix server-self-hosted job (#28603)

    * ci : add PYTEST_WORKERS=1 to fix server-self-hosted job

    This commit adds the `PYTEST_WORKERS=1` environment variable to the
    hf-jobs-t4-small:cuda13 runner steps.

    This is an attempt to address CI failure of this job that I might have
    introduced in Commit 42f0225fea945b24e92a0ce716e59b7c13e9b819
    ("server : use pytest-xdist for server tests (#28298)").

    Refs: https://github.com/ggml-org/llama.cpp/actions/runs/34126971262/job/101757819134

    * apply same changes to server-metal steps

diff --git a/.github/workflows/server-self-hosted.yml b/.github/workflows/server-self-hosted.yml
index d9ad2fcd0..de30d1a74 100644
--- a/.github/workflows/server-self-hosted.yml
+++ b/.github/workflows/server-self-hosted.yml
@@ -72,7 +72,7 @@ jobs:
         run: |
           cd tools/server/tests
           source venv/bin/activate
-          ./tests.sh
+          PYTEST_WORKERS=1 ./tests.sh

       - name: Tests (GPUx1, backend-sampling)
         id: server_integration_tests_backend_sampling
@@ -81,7 +81,7 @@ jobs:
           cd tools/server/tests
           source venv/bin/activate
           export LLAMA_ARG_BACKEND_SAMPLING=1
-          ./tests.sh
+          PYTEST_WORKERS=1 ./tests.sh

       - name: Tests (GPUx2)
         id: server_integration_tests_gpu2
@@ -90,7 +90,7 @@ jobs:
           cd tools/server/tests
           source venv/bin/activate
           export GGML_METAL_DEVICES=2
-          ./tests.sh
+          PYTEST_WORKERS=1 ./tests.sh

       - name: Tests (GPUx2, backend-sampling)
         id: server_integration_tests_gpu2_backend_sampling
@@ -99,7 +99,7 @@ jobs:
           cd tools/server/tests
           source venv/bin/activate
           export GGML_METAL_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1
-          ./tests.sh
+          PYTEST_WORKERS=1 ./tests.sh

   server-cuda:
     runs-on: "hf-jobs-t4-small:cuda13"
@@ -162,7 +162,7 @@ jobs:
         run: |
           cd tools/server/tests
           source venv/bin/activate
-          ./tests.sh
+          PYTEST_WORKERS=1 ./tests.sh

       - name: Tests (GPUx1, backend-sampling)
         id: server_integration_tests_backend_sampling
@@ -171,7 +171,7 @@ jobs:
           cd tools/server/tests
           source venv/bin/activate
           export LLAMA_ARG_BACKEND_SAMPLING=1
-          ./tests.sh
+          PYTEST_WORKERS=1 ./tests.sh

       - name: Tests (GPUx2)
         id: server_integration_tests_gpu2
@@ -180,7 +180,7 @@ jobs:
           cd tools/server/tests
           source venv/bin/activate
           export GGML_CUDA_DEVICES=2
-          ./tests.sh
+          PYTEST_WORKERS=1 ./tests.sh

       - name: Tests (GPUx2, backend-sampling)
         id: server_integration_tests_gpu2_backend_sampling
@@ -189,7 +189,7 @@ jobs:
           cd tools/server/tests
           source venv/bin/activate
           export GGML_CUDA_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1
-          ./tests.sh
+          PYTEST_WORKERS=1 ./tests.sh

   server-kleidiai:
     runs-on: ah-ubuntu_22_04-c8g_8x