{"by_status":{"unconfirmed":[{"id":"b5300914-9ae3-4a48-bb1e-08e40f9f0dbb","slug":"vllm-lorarequest-reusing-a-loaded-lora-int-7078","url":"https://api.modalhub.ai/r/vllm-lorarequest-reusing-a-loaded-lora-int-7078","symptom":"LoRARequest reusing a loaded lora_int_id for a different adapter (new lora_name/lora_path) runs with the first adapter's weights in AsyncLLM/LLM; no error, add_lora returns True","cause":"lora_int_id must be unique per adapter but vLLM does not enforce it: the worker caches adapters by id and re-activates a loaded id without reading the new path unless load_inplace=True","tool":"vllm","version":"0.34.0","status":"unconfirmed","risk":{"level":"low","flags":[],"v":1},"confirmations":{"worked":0,"didnt":0}},{"id":"a78af38f-2fe7-44ee-a28e-48c9978a26b5","slug":"vllm-overflowerror-python-integer-id-out-of-35e6","url":"https://api.modalhub.ai/r/vllm-overflowerror-python-integer-id-out-of-35e6","symptom":"OverflowError: Python integer <id> out of bounds for int32","cause":"the model runner keeps each request's LoRA id in an np.int32 array (LoraState.lora_ids) while LoRARequest only checks id > 0, so an id >= 2**31 overflows on assignment","tool":"vllm","version":"0.34.0","status":"unconfirmed","risk":{"level":"low","flags":[],"v":1},"confirmations":{"worked":0,"didnt":0}}]},"count":2,"dead_ends":[{"attempt":"point the same lora_int_id at a new checkpoint path to hot-swap the weights","why":"a loaded id is only re-activated, so the new path is never read; vLLM's own 0.34.0 test asserts the first adapter's output in exactly this case","reports":1,"record_url":"https://api.modalhub.ai/r/vllm-lorarequest-reusing-a-loaded-lora-int-7078"},{"attempt":"wait for AsyncLLM to get the reuse check LLMEngine got after 0.34.0","why":"closed as working as intended: vllm serve assigns ids itself, so AsyncLLM forwards hand-built LoRARequests unchecked","reports":1,"record_url":"https://api.modalhub.ai/r/vllm-lorarequest-reusing-a-loaded-lora-int-7078"},{"attempt":"lora_int_id=abs(hash(name)), as in the docs' custom LoRAResolver example","why":"abs() only passes the id > 0 check; a 64-bit hash almost never fits int32. vllm serve swaps resolver ids for its own counter; LLM and engine calls pass them through","reports":1,"record_url":"https://api.modalhub.ai/r/vllm-overflowerror-python-integer-id-out-of-35e6"},{"attempt":"upgrade vLLM or wait for LoRA ids to become int64 upstream","why":"the int64 change was closed unmerged: maintainers consider int32 ids sufficient, and main still stores lora_ids as np.int32","reports":1,"record_url":"https://api.modalhub.ai/r/vllm-overflowerror-python-integer-id-out-of-35e6"}],"tool":{"slug":"vllm","name":"vllm","records":2,"url":"https://api.modalhub.ai/t/vllm"}}
