[V1] Simpify vision block hash for prefix caching by removing offset from hash (#11646)

2024-12-31 16:56:01 +08:00
parent 2c5718809b
commit 8c3230d8c1
2 changed files with 6 additions and 6 deletions
--- a/vllm/v1/core/kv_cache_utils.py
+++ b/vllm/v1/core/kv_cache_utils.py
@@ -218,8 +218,8 @@ def generate_block_hash_extra_keys(
                continue

            # The block contains the current mm input.
-            mm_start = max(0, start_token_idx - offset)
-            extra_keys.append((mm_hashes[curr_mm_idx], mm_start))
+            extra_keys.append(mm_hashes[curr_mm_idx])
+
            if end_token_idx >= offset + length:
                # If this block contains the end of the current mm input,
                # move to the next mm input as this block may also contain