Load test setup from config files, fix correctness, enable plugin in V1

Makefile

@@ -3,7 +3,7 @@ MAX_JOBS := 64
 
 SHELL := /bin/bash
 
-.PHONY: all build clean format dev rocm rocm-upstream pyupdate nightly bm-rocm
+.PHONY: all build clean format dev rocm rocm-upstream pyupdate nightly bm-rocm spelling
 
 all: build
 
@@ -65,3 +65,7 @@ else
 format:
 	python -m black --check --verbose scripts ibm-triton-lib third_party
 endif
+
+spelling:
+	codespell ./ibm-triton-lib ./triton-dejavu ./scripts
+

ibm-triton-lib/ibm_triton_lib/backend/__init__.py

@@ -19,11 +19,4 @@
 
 def register():
     """Register the triton attention platform."""
-
-    VLLM_USE_V1 = int(os.environ.get("VLLM_USE_V1", "0"))
-
-    # backend only works with v0 currently
-    if VLLM_USE_V1:
-        return None
-    else:
-        return "ibm_triton_lib.backend.platform.TritonPlatform"
+    return "ibm_triton_lib.backend.platform.TritonPlatform"

ibm-triton-lib/ibm_triton_lib/backend/platform.py

@@ -61,4 +61,6 @@ def get_attn_backend_cls(
         use_v1,
         use_mla,
     ) -> str:
+        if not envs.VLLM_USE_V1:
+            raise RuntimeError("vllm-triton-backend plugin only supports vLLM V1")
         return "ibm_triton_lib.backend.triton_attn.TritonAttentionBackend"