[CI/Build][SM70] Close wheel build inputs

docker/Dockerfile

@@ -344,6 +344,7 @@ WORKDIR /workspace
 COPY pyproject.toml setup.py CMakeLists.txt ./
 COPY cmake cmake/
 COPY csrc csrc/
+COPY flash_qla flash_qla/
 COPY vllm/envs.py vllm/envs.py
 COPY vllm/__init__.py vllm/__init__.py
 

requirements/cuda.txt

@@ -24,8 +24,8 @@ fastsafetensors >= 0.3.3
 nvidia-cutlass-dsl[cu13]==4.7.0
 quack-kernels>=0.3.3
 
-# Tokenspeed_MLA for faster mla with spec decode
-tokenspeed-mla==0.2.5
+# TokenSpeed MLA is optional. Version 0.2.5 pins apache-tvm-ffi==0.1.13,
+# which cannot coexist with the TileLang version pinned above.
 
 # Humming kernels for quantization gemm
 humming-kernels[cu13]==0.1.2

vllm/v1/attention/backends/mla/prefill/tokenspeed_mla.py

@@ -30,8 +30,9 @@ def supports_compute_capability(cls, device_capability: "DeviceCapability") -> b
         return device_capability.major == 10
 
     _INSTALL_HINT = (
-        "tokenspeed_mla package is not installed. "
-        "Install it with: `uv pip install tokenspeed-mla`"
+        "tokenspeed_mla is an optional package and is not installed. "
+        "Its apache-tvm-ffi requirement must be compatible with the installed "
+        "TileLang version."
     )
 
     @classmethod

vllm/v1/attention/backends/mla/tokenspeed_mla.py

@@ -101,8 +101,9 @@ def supports_combination(
             import tokenspeed_mla  # noqa: F401
         except ImportError:
             return (
-                "tokenspeed_mla package is not installed. "
-                "Install it with: `uv pip install tokenspeed-mla`"
+                "tokenspeed_mla is an optional package and is not installed. "
+                "Its apache-tvm-ffi requirement must be compatible with the "
+                "installed TileLang version."
             )
 
         # tokenspeed_mla CuTe DSL kernel is shape-specialized for DeepSeek R1