small fixes

vllm-project · Aug 27, 2024 · d312acb · d312acb
1 parent dd38054
commit d312acb
Show file tree

Hide file tree

Showing 2 changed files with 1 addition and 5 deletions.
diff --git a/examples/offline_inference.py b/examples/offline_inference.py
@@ -11,10 +11,7 @@
 sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
 
 # Create an LLM.
-llm = LLM(model="facebook/opt-125m",
-          num_scheduler_steps=8,
-          use_v2_block_manager=True,
-          disable_async_output_proc=False)
+llm = LLM(model="facebook/opt-125m")
 # Generate texts from the prompts. The output is a list of RequestOutput objects
 # that contain the prompt, generated text, and other information.
 outputs = llm.generate(prompts, sampling_params)

diff --git a/vllm/core/scheduler.py b/vllm/core/scheduler.py
@@ -1105,7 +1105,6 @@ def schedule(
         if not self.cache_config.enable_prefix_caching:
             common_computed_block_nums = []
 
-        # TODO: Combine multi-step and async postprocessor
         allow_async_output_proc: bool = self.use_async_output_proc
 
         # Create input data structures.