Unverified Commit 4e4d017b authored by Hyogeun Oh (오효근)'s avatar Hyogeun Oh (오효근) Committed by GitHub
Browse files

[Docs] Fix warnings in `mkdocs build` (continued) (#23743)


Signed-off-by: default avatarZerohertz <ohg3417@gmail.com>
Signed-off-by: default avatarHyogeun Oh (오효근) <ohg3417@gmail.com>
parent dd589322
......@@ -525,9 +525,6 @@ class InputBatch:
Any consecutive empty indices at the very end of the list are not
filled.
Args:
empty_req_indices: empty indices which may be filled.
Returns:
swaps: list of (from,to) swap tuples for moved requests
empty_req_indices: indices not filled by condensation
......
......@@ -552,7 +552,7 @@ class TPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
return kv_cache_spec
def _get_slot_mapping_metadata(self, num_reqs,
num_scheduled_tokens_per_req):
num_scheduled_tokens_per_req) -> np.ndarray:
"""
Computes metadata for mapping slots to blocks in the key-value (KV)
cache for a batch of requests.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment