[None][feat] Add NIXL-LIBFABRIC support (NVIDIA#9225)

Signed-off-by: Yoray Zack <[email protected]>
Signed-off-by: zackyoray <[email protected]>

Author: zackyoray

cpp/tensorrt_llm/executor/cache_transmission/nixl_utils/transferAgent.cpp

@@ -348,11 +348,11 @@ NixlTransferAgent::NixlTransferAgent(BaseAgentConfig const& config)
 
     std::string nixlBackend = common::getEnvNixlBackend();
     // List of supported backends - extend this list as new backends are added
-    static const std::set<std::string> kSUPPORTED_BACKENDS = {"UCX"};
+    static const std::set<std::string> kSUPPORTED_BACKENDS = {"UCX", "LIBFABRIC"};
 
     if (kSUPPORTED_BACKENDS.find(nixlBackend) == kSUPPORTED_BACKENDS.end())
     {
-        TLLM_LOG_ERROR("Unsupported NIXL backend: %s, fallback to UCX", nixlBackend.c_str());
+        TLLM_LOG_WARNING("Unsupported NIXL backend: %s, fallback to UCX", nixlBackend.c_str());
         nixlBackend = "UCX";
     }
 

docker/common/install_nixl.sh

@@ -38,7 +38,8 @@ meson setup builddir \
     -Dcudapath_lib="$CUDA_PATH/lib64" \
     -Dcudapath_inc="$CUDA_PATH/include" \
     -Dgds_path="$GDS_PATH" \
-    -Dinstall_headers=true
+    -Dinstall_headers=true \
+    --buildtype=release
 
 cd builddir && ninja install
 cd ../..

jenkins/current_image_tags.properties

@@ -13,7 +13,7 @@
 #     images are adopted from PostMerge pipelines, the abbreviated commit hash is used instead.
 IMAGE_NAME=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm
 
-LLM_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.10-py3-x86_64-ubuntu24.04-trt10.13.3.9-skip-tritondevel-202511281406-9077
-LLM_SBSA_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.10-py3-aarch64-ubuntu24.04-trt10.13.3.9-skip-tritondevel-202511281406-9077
-LLM_ROCKYLINUX8_PY310_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-13.0.2-devel-rocky8-x86_64-rocky8-py310-trt10.13.3.9-skip-tritondevel-202511281406-9077
-LLM_ROCKYLINUX8_PY312_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-13.0.2-devel-rocky8-x86_64-rocky8-py312-trt10.13.3.9-skip-tritondevel-202511281406-9077
+LLM_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.10-py3-x86_64-ubuntu24.04-trt10.13.3.9-skip-tritondevel-202512041415-9225
+LLM_SBSA_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.10-py3-aarch64-ubuntu24.04-trt10.13.3.9-skip-tritondevel-202512041415-9225
+LLM_ROCKYLINUX8_PY310_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-13.0.2-devel-rocky8-x86_64-rocky8-py310-trt10.13.3.9-skip-tritondevel-202512041415-9225
+LLM_ROCKYLINUX8_PY312_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-13.0.2-devel-rocky8-x86_64-rocky8-py312-trt10.13.3.9-skip-tritondevel-202512041415-9225