A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 23:30 UTC
[V1][Minor] Remove outdated comment (#12968)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Woosuk Kwon committed
Feb 8, 2025 at 12:48 UTC
870c37481e4d9dbcd548344e1eee6bd83993388a
1 file changed
-2
vllm/v1/core/kv_cache_manager.py
-2
@@ -205,8 +205,6 @@ class KVCacheManager:
205
# Should not exceed the maximum number of blocks per request.
206
# This is especially because the block table has the shape
207
# [..., max_num_blocks_per_req].
208
- # TODO(woosuk): Check and reject requests if
209
- # num_prompt_tokens + max_tokens > max_model_len.
208
self.max_num_blocks_per_req - len(req_blocks),
209
)
210
assert num_new_blocks > 0