[Core] Non Unit Instance fractional value fix

doc/source/ray-core/scheduling/resources.rst

@@ -194,3 +194,7 @@ The precision of the fractional resource requirement is 0.0001 so you should avo
 
   Besides resource requirements, you can also specify an environment for a task or actor to run in,
   which can include Python packages, local files, environment variables, and more---see :ref:`Runtime Environments <runtime-environments>` for details.
+
+.. note::
+  For any unit resource (Resources assigned by scheduler using ids such as GPU, TPU, Neuron Core) requirement greater than 1, 
+  it needs to be a whole number (e.g. ``num_gpus=1.5`` is invalid).

python/ray/_raylet.pyx

@@ -640,10 +640,14 @@ cdef int prepare_resources(
         if value < 0:
             raise ValueError("Resource quantities may not be negative.")
         if value > 0:
+            unit_resources = f"{RayConfig.instance().predefined_unit_instance_resources()},\
+            {RayConfig.instance().custom_unit_instance_resources()}"
+
             if (value >= 1 and isinstance(value, float)
-                    and not value.is_integer()):
+                    and not value.is_integer() and str(key) in unit_resources):
                 raise ValueError(
-                    "Resource quantities >1 must be whole numbers.")
+                    "Unit instance resource (GPU, TPU, Neuron Core) quantities >1 must",
+                    f" be whole numbers. {key} resource with value {value} is invalid.")
             resource_map[0][key.encode("ascii")] = float(value)
     return 0
 

python/ray/includes/ray_config.pxd

@@ -92,3 +92,7 @@ cdef extern from "ray/common/ray_config.h" nogil:
         int64_t grpc_client_keepalive_timeout_ms() const
 
         c_bool enable_autoscaler_v2() const
+
+        c_string predefined_unit_instance_resources() const
+
+        c_string custom_unit_instance_resources() const

python/ray/tests/test_advanced_2.py

@@ -147,7 +147,7 @@ def method(self):
 
 
 def test_fractional_resources(shutdown_only):
-    ray.init(num_cpus=6, num_gpus=3, resources={"Custom": 1})
+    ray.init(num_cpus=6, num_gpus=3, resources={"Custom": 3, "TPU": 3})
 
     @ray.remote(num_gpus=0.5)
     class Foo1:
@@ -168,7 +168,7 @@ def method(self):
             pass
 
     # Create an actor that requires 0.7 of the custom resource.
-    f1 = Foo2._remote([], {}, resources={"Custom": 0.7})
+    f1 = Foo2._remote([], {}, resources={"Custom": 2.7})
     ray.get(f1.method.remote())
     # Make sure that we cannot create an actor that requires 0.7 of the
     # custom resource. TODO(rkn): Re-enable this once ray.wait is
@@ -183,18 +183,25 @@ def method(self):
 
     del f1, f3
 
-    # Make sure that we get exceptions if we submit tasks that require a
-    # fractional number of resources greater than 1.
+    # Non unit resources (e.g. CPU, ) allow fractional
+    # number of resources greather than 1.
+    @ray.remote(num_cpus=1.5, resources={"Custom": 2.5})
+    def test_frac_cpu():
+        return True
 
-    @ray.remote(num_cpus=1.5)
-    def test():
+    assert ray.get(test_frac_cpu.remote())
+
+    # Unit instance resources (GPU, TPU, neuron_core) throw exceptions
+    # for fractional number of resources greater than 1.
+    @ray.remote(num_gpus=1.5)
+    def test_frac_gpu():
         pass
 
     with pytest.raises(ValueError):
-        test.remote()
+        test_frac_gpu.remote()
 
     with pytest.raises(ValueError):
-        Foo2._remote([], {}, resources={"Custom": 1.5})
+        Foo2._remote([], {}, resources={"TPU": 2.5})
 
 
 def test_fractional_memory_round_down(shutdown_only):