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 16, 00:45 UTC
[V1][Bugfix] Fix assertion when mm hashing is turned off (#12439)
Signed-off-by: Roger Wang <ywang@roblox.com>
Roger Wang committed
Jan 26, 2025 at 00:47 UTC
0ee349b5534e3d02b499b1126f2abde73b798fe9
1 file changed
+2
-1
vllm/v1/request.py
+2
-1
@@ -58,7 +58,8 @@ class Request:
58
59
# Sanity check
60
assert len(self.mm_inputs) == len(self.mm_positions)
61
- assert len(self.mm_inputs) == len(self.mm_hashes)
61
+ if self.mm_hashes:
62
+ assert len(self.mm_inputs) == len(self.mm_hashes)
63
64
# Cache the computed kv block hashes of the request to avoid
65
# recomputing.