fix some typos (#6209)

Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>

python/sglang/srt/managers/scheduler.py

@@ -1667,7 +1667,7 @@ class Scheduler(
             can_cuda_graph = 0
 
         if not spec_algorithm.is_none():
-            # TODO(sang): Support cuda graph when idle batch is there.
+            # TODO(sang): Support CUDA graph when idle batch is there.
             if local_batch is None or local_batch.forward_mode.is_idle():
                 can_cuda_graph = 0
 
@@ -1704,7 +1704,7 @@ class Scheduler(
             local_batch.global_num_tokens = global_num_tokens
             local_batch.global_num_tokens_for_logprob = global_num_tokens_for_logprob
 
-            # Check forward mode for cuda graph
+            # Check forward mode for CUDA graph
             if not disable_cuda_graph:
                 local_batch.can_run_dp_cuda_graph = can_cuda_graph
 

python/sglang/srt/managers/tokenizer_manager.py

@@ -238,7 +238,7 @@ class TokenizerManager:
             self.metrics_collector = TokenizerMetricsCollector(
                 labels={
                     "model_name": self.server_args.served_model_name,
-                    # TODO: Add lora name/path in the future,
+                    # TODO: Add LoRA name/path in the future,
                 },
             )
 

python/sglang/srt/managers/tp_worker_overlap_thread.py

@@ -213,7 +213,7 @@ class TpModelWorkerClient:
             penalizer_orchestrator=None,
         )
 
-        # A cuda stream sync here to avoid the cuda illegal memory access error.
+        # A CUDA stream sync here to avoid the CUDA illegal memory access error.
         self.scheduler_stream.synchronize()
 
         # Push a new batch to the queue