[V1][Minor] Remove outdated comment (vllm-project#12968)

WoosukKwon · lulmer · commit 9ed7b4d836bd · 2025-04-07T07:38:17.000Z
Signed-off-by: Woosuk Kwon &lt;woosuk.kwon@berkeley.edu&gt;
Signed-off-by: Louis Ulmer &lt;ulmerlouis@gmail.com&gt;
diff --git a/vllm/v1/core/kv_cache_manager.py b/vllm/v1/core/kv_cache_manager.py
@@ -205,8 +205,6 @@ def allocate_slots(
                 # Should not exceed the maximum number of blocks per request.
                 # This is especially because the block table has the shape
                 # [..., max_num_blocks_per_req].
-                # TODO(woosuk): Check and reject requests if
-                # num_prompt_tokens + max_tokens > max_model_len.
                 self.max_num_blocks_per_req - len(req_blocks),
             )
             assert num_new_blocks > 0

Original file line number	Diff line number	Diff line change
`@@ -205,8 +205,6 @@ def allocate_slots(`
`205`	`205`	`# Should not exceed the maximum number of blocks per request.`
`206`	`206`	`# This is especially because the block table has the shape`
`207`	`207`	`# [..., max_num_blocks_per_req].`
`208`		`- # TODO(woosuk): Check and reject requests if`
`209`		`- # num_prompt_tokens + max_tokens > max_model_len.`
`210`	`208`	`self.max_num_blocks_per_req - len(req_blocks),`
`211`	`209`	`)`
`212`	`210`	`assert num_new_blocks > 0`