From 0861fb266161bbb86692d9fa1eb57cf471d15023 Mon Sep 17 00:00:00 2001 From: Woosuk Kwon Date: Sat, 8 Feb 2025 11:54:18 -0800 Subject: [PATCH] [V1][Minor] Remove outdated comment Signed-off-by: Woosuk Kwon --- vllm/v1/core/kv_cache_manager.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/vllm/v1/core/kv_cache_manager.py b/vllm/v1/core/kv_cache_manager.py index eefc2e19c20a..f8d08d0e4023 100644 --- 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