fix(cuda): install cuda-nvrtc-dev alongside the other CUDA dev packages (#10257)

Signed-off-by: pos-ei-don <1822533+pos-ei-don@users.noreply.github.com>

Dockerfile

@@ -108,6 +108,7 @@ RUN <<EOT bash
         apt-get update && \
         apt-get install -y --no-install-recommends \
             cuda-nvcc-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
+            cuda-nvrtc-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
             libcufft-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
             libcurand-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
             libcublas-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \

backend/Dockerfile.python

@@ -126,6 +126,7 @@ RUN <<EOT bash
         apt-get update && \
         apt-get install -y --no-install-recommends \
             cuda-nvcc-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
+            cuda-nvrtc-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
             libcufft-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
             libcurand-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
             libcublas-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=039e20a2db9e87b2477c76cc04905f3e1acad77f
+LLAMA_VERSION?=ac4cddeb0dbd778f650bf568f6f08344a06abe3a
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

backend/go/crispasr/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # CrispASR version (release tag)
 CRISPASR_REPO?=https://github.com/CrispStrobe/CrispASR
-CRISPASR_VERSION?=c29f6653a516a3001d923944dad8892072cc7334
+CRISPASR_VERSION?=4b27392ffd0991a857594652cbb8b57e585bcd7b
 SO_TARGET?=libgocrispasr.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

backend/python/vllm/backend.py

@@ -150,9 +150,24 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                 d["reasoning_content"] = msg.reasoning_content
             if msg.tool_calls:
                 try:
-                    d["tool_calls"] = json.loads(msg.tool_calls)
+                    tool_calls = json.loads(msg.tool_calls)
                 except json.JSONDecodeError:
                     pass
+                else:
+                    # OpenAI wire format carries function.arguments as a
+                    # JSON-encoded string, but chat templates (e.g. Qwen3)
+                    # iterate over it as a mapping. vLLM's own OpenAI server
+                    # parses arguments before applying the template, so do
+                    # the same here.
+                    if isinstance(tool_calls, list):
+                        for tc in tool_calls:
+                            func = tc.get("function") if isinstance(tc, dict) else None
+                            if isinstance(func, dict) and isinstance(func.get("arguments"), str):
+                                try:
+                                    func["arguments"] = json.loads(func["arguments"])
+                                except json.JSONDecodeError:
+                                    pass
+                    d["tool_calls"] = tool_calls
             result.append(d)
         return result
 

docs/content/advanced/model-configuration.md

@@ -429,7 +429,7 @@ name: my-model
 reasoning_effort: none   # none | minimal | low | medium | high
 ```
 
-For [realtime pipelines]({{%relref "docs/features/openai-realtime" %}}), set it on the pipeline so it applies to the pipeline's LLM without editing that model's own config:
+For [realtime pipelines]({{%relref "features/openai-realtime" %}}), set it on the pipeline so it applies to the pipeline's LLM without editing that model's own config:
 
 ```yaml
 name: gpt-realtime