[CUDAX] Add an event constructor taking a device_ref

[pciolkosz]

Currently event can only be constructed with a stream and it comes pre-recorded into that stream. This PR adds an event constructor taking device_ref to produce an event not recorded to any stream.
Hopefully in the future it would be possible to create an event not tied to a specific device, but until then construction from device_ref is the best we can do.

[github-actions]

🟩 CI finished in 18m 26s: Pass: 100%/30 | Total: 3h 23m | Avg: 6m 46s | Max: 16m 23s | Hits: 83%/15234

• 🟩 cudax: Pass: 100%/26 | Total: 3h 10m | Avg: 7m 19s | Max: 16m 23s | Hits: 83%/15234

  🟩 cpu
    🟩 amd64              Pass: 100%/22  | Total:  2h 47m | Avg:  7m 35s | Max: 16m 23s | Hits:  83%/12798 
    🟩 arm64              Pass: 100%/4   | Total: 23m 27s | Avg:  5m 51s | Max:  6m 32s | Hits:  82%/2436  
  🟩 ctk
    🟩 12.0               Pass: 100%/3   | Total: 25m 07s | Avg:  8m 22s | Max: 15m 04s | Hits:  78%/1526  
    🟩 12.9               Pass: 100%/23  | Total:  2h 45m | Avg:  7m 11s | Max: 16m 23s | Hits:  83%/13708 
  🟩 cudacxx
    🟩 nvcc12.0           Pass: 100%/3   | Total: 25m 07s | Avg:  8m 22s | Max: 15m 04s | Hits:  78%/1526  
    🟩 nvcc12.9           Pass: 100%/23  | Total:  2h 45m | Avg:  7m 11s | Max: 16m 23s | Hits:  83%/13708 
  🟩 cudacxx_family
    🟩 nvcc               Pass: 100%/26  | Total:  3h 10m | Avg:  7m 19s | Max: 16m 23s | Hits:  83%/15234 
  🟩 cxx
    🟩 Clang14            Pass: 100%/2   | Total: 10m 13s | Avg:  5m 06s | Max:  5m 32s | Hits:  82%/1220  
    🟩 Clang15            Pass: 100%/1   | Total:  6m 13s | Avg:  6m 13s | Max:  6m 13s | Hits:  82%/609   
    🟩 Clang16            Pass: 100%/1   | Total:  5m 56s | Avg:  5m 56s | Max:  5m 56s | Hits:  82%/609   
    🟩 Clang17            Pass: 100%/1   | Total:  5m 57s | Avg:  5m 57s | Max:  5m 57s | Hits:  82%/609   
    🟩 Clang18            Pass: 100%/1   | Total:  6m 09s | Avg:  6m 09s | Max:  6m 09s | Hits:  82%/609   
    🟩 Clang19            Pass: 100%/4   | Total: 24m 42s | Avg:  6m 10s | Max:  8m 12s | Hits:  86%/2436  
    🟩 GCC10              Pass: 100%/2   | Total: 11m 31s | Avg:  5m 45s | Max:  6m 09s | Hits:  82%/1220  
    🟩 GCC11              Pass: 100%/1   | Total:  6m 24s | Avg:  6m 24s | Max:  6m 24s | Hits:  81%/609   
    🟩 GCC12              Pass: 100%/1   | Total:  7m 02s | Avg:  7m 02s | Max:  7m 02s | Hits:  81%/609   
    🟩 GCC13              Pass: 100%/8   | Total: 53m 58s | Avg:  6m 44s | Max:  9m 58s | Hits:  86%/4872  
    🟩 MSVC14.39          Pass: 100%/1   | Total: 15m 04s | Avg: 15m 04s | Max: 15m 04s | Hits:  61%/308   
    🟩 MSVC14.43          Pass: 100%/1   | Total: 16m 23s | Avg: 16m 23s | Max: 16m 23s | Hits:  60%/310   
    🟩 NVHPC25.5          Pass: 100%/2   | Total: 21m 03s | Avg: 10m 31s | Max: 10m 53s | Hits:  79%/1214  
  🟩 cxx_family
    🟩 Clang              Pass: 100%/10  | Total: 59m 10s | Avg:  5m 55s | Max:  8m 12s | Hits:  84%/6092  
    🟩 GCC                Pass: 100%/12  | Total:  1h 18m | Avg:  6m 34s | Max:  9m 58s | Hits:  85%/7310  
    🟩 MSVC               Pass: 100%/2   | Total: 31m 27s | Avg: 15m 43s | Max: 16m 23s | Hits:  61%/618   
    🟩 NVHPC              Pass: 100%/2   | Total: 21m 03s | Avg: 10m 31s | Max: 10m 53s | Hits:  79%/1214  
  🟩 gpu
    🟩 h100               Pass: 100%/2   | Total: 15m 17s | Avg:  7m 38s | Max:  9m 58s | Hits:  90%/1218  
    🟩 rtx2080            Pass: 100%/24  | Total:  2h 55m | Avg:  7m 18s | Max: 16m 23s | Hits:  82%/14016 
  🟩 jobs
    🟩 Build              Pass: 100%/23  | Total:  2h 42m | Avg:  7m 04s | Max: 16m 23s | Hits:  80%/13407 
    🟩 Test               Pass: 100%/3   | Total: 27m 55s | Avg:  9m 18s | Max:  9m 58s | Hits:  99%/1827  
  🟩 sm
    🟩 90                 Pass: 100%/3   | Total: 19m 44s | Avg:  6m 34s | Max:  9m 58s | Hits:  87%/1827  
    🟩 90a                Pass: 100%/1   | Total:  4m 59s | Avg:  4m 59s | Max:  4m 59s | Hits:  81%/609   
  🟩 std
    🟩 17                 Pass: 100%/4   | Total: 26m 10s | Avg:  6m 32s | Max: 10m 10s | Hits:  81%/2434  
    🟩 20                 Pass: 100%/22  | Total:  2h 44m | Avg:  7m 28s | Max: 16m 23s | Hits:  83%/12800 
  

• 🟩 packaging: Pass: 100%/4 | Total: 12m 49s | Avg: 3m 12s | Max: 3m 23s

  🟩 cpu
    🟩 amd64              Pass: 100%/4   | Total: 12m 49s | Avg:  3m 12s | Max:  3m 23s
  🟩 ctk
    🟩 12.0               Pass: 100%/2   | Total:  6m 32s | Avg:  3m 16s | Max:  3m 23s
    🟩 12.9               Pass: 100%/2   | Total:  6m 17s | Avg:  3m 08s | Max:  3m 21s
  🟩 cudacxx
    🟩 nvcc12.0           Pass: 100%/2   | Total:  6m 32s | Avg:  3m 16s | Max:  3m 23s
    🟩 nvcc12.9           Pass: 100%/2   | Total:  6m 17s | Avg:  3m 08s | Max:  3m 21s
  🟩 cudacxx_family
    🟩 nvcc               Pass: 100%/4   | Total: 12m 49s | Avg:  3m 12s | Max:  3m 23s
  🟩 cxx
    🟩 Clang14            Pass: 100%/1   | Total:  3m 23s | Avg:  3m 23s | Max:  3m 23s
    🟩 Clang19            Pass: 100%/1   | Total:  3m 21s | Avg:  3m 21s | Max:  3m 21s
    🟩 GCC12              Pass: 100%/1   | Total:  3m 09s | Avg:  3m 09s | Max:  3m 09s
    🟩 GCC13              Pass: 100%/1   | Total:  2m 56s | Avg:  2m 56s | Max:  2m 56s
  🟩 cxx_family
    🟩 Clang              Pass: 100%/2   | Total:  6m 44s | Avg:  3m 22s | Max:  3m 23s
    🟩 GCC                Pass: 100%/2   | Total:  6m 05s | Avg:  3m 02s | Max:  3m 09s
  🟩 gpu
    🟩 rtx2080            Pass: 100%/4   | Total: 12m 49s | Avg:  3m 12s | Max:  3m 23s
  🟩 jobs
    🟩 Test               Pass: 100%/4   | Total: 12m 49s | Avg:  3m 12s | Max:  3m 23s
  

👃 Inspect Changes

Modifications in project?

	Project
	CCCL Infrastructure
	CCCL Packaging
	libcu++
	CUB
	Thrust
+/-	CUDA Experimental
	stdpar
	python
	CCCL C Parallel Library
	Catch2Helper

Modifications in project or dependencies?

	Project
	CCCL Infrastructure
+/-	CCCL Packaging
	libcu++
	CUB
	Thrust
+/-	CUDA Experimental
	stdpar
	python
	CCCL C Parallel Library
	Catch2Helper

🏃‍ Runner counts (total jobs: 30)

#	Runner
17	linux-amd64-cpu16
6	linux-amd64-gpu-rtx2080-latest-1
4	linux-arm64-cpu16
2	windows-amd64-cpu16
1	linux-amd64-gpu-h100-latest-1