From 43be004379fc2738c9066c84aecb4e6cc41dbf1a Mon Sep 17 00:00:00 2001 From: Li Wang Date: Mon, 26 Jan 2026 17:54:00 +0800 Subject: [PATCH] [Lint] Fix mypy issue to make CI happy (#6272) ### What this PR does / why we need it? The variables `self.prefiller_heap` `self.decoder_heap` are used as `List[tuple[float, int, ServerState]]` but defined as `List[tuple[int, int, ServerState]]`, which leads to the failed of mypy, see https://github.com/vllm-project/vllm-ascend/actions/runs/21351411010/job/61448739554?pr=6265 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.14.1 - vLLM main: https://github.com/vllm-project/vllm/commit/d68209402ddab3f54a09bc1f4de9a9495a283b60 Signed-off-by: wangli --- .../load_balance_proxy_server_example.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py b/examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py index 0af2c962..d339c484 100644 --- a/examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py +++ b/examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py @@ -209,8 +209,8 @@ class ProxyState: # Initialize priority queues for efficient server selection # Each entry is (priority_score, server_index, server_reference) # Lower priority score = higher priority (less loaded) - self.prefiller_heap = [(0, i, server) for i, server in enumerate(self.prefillers)] - self.decoder_heap = [(0, i, server) for i, server in enumerate(self.decoders)] + self.prefiller_heap = [(0.0, i, server) for i, server in enumerate(self.prefillers)] + self.decoder_heap = [(0.0, i, server) for i, server in enumerate(self.decoders)] heapq.heapify(self.prefiller_heap) heapq.heapify(self.decoder_heap) @@ -221,7 +221,7 @@ class ProxyState: priority = server.active_tokens + server.active_kv_cache * 0.3 # Remove old entry and add new one self.prefiller_heap = [(p, i, s) for p, i, s in self.prefiller_heap if i != server_idx] - heapq.heappush(self.prefiller_heap, (priority, server_idx, server)) # type: ignore + heapq.heappush(self.prefiller_heap, (priority, server_idx, server)) def _update_decoder_priority(self, server_idx: int): """Update the priority of a decoder server in the heap.""" @@ -229,7 +229,7 @@ class ProxyState: priority = server.active_tokens # Remove old entry and add new one self.decoder_heap = [(p, i, s) for p, i, s in self.decoder_heap if i != server_idx] - heapq.heappush(self.decoder_heap, (priority, server_idx, server)) # type: ignore + heapq.heappush(self.decoder_heap, (priority, server_idx, server)) def abort_prefiller_request(self, server_idx: int, request_id): # Changed to synchronous """