diff --git a/vllm/v1/attention/backends/mla/indexer.py b/vllm/v1/attention/backends/mla/indexer.py index 828f2c2ac4..2321cf8d13 100644 --- a/vllm/v1/attention/backends/mla/indexer.py +++ b/vllm/v1/attention/backends/mla/indexer.py @@ -771,15 +771,6 @@ class DeepseekV32IndexerMetadataBuilder(AttentionMetadataBuilder): self.pcp_world_size = parallel_config.prefill_context_parallel_size self.use_pcp = self.pcp_world_size > 1 self.cp_kv_cache_interleave_size = parallel_config.cp_kv_cache_interleave_size - # The DCP sparse-indexer code is parameterized by interleave size, but - # interleave > 1 is not yet validated end-to-end (gsm8k parity fails), - # so fail closed here rather than silently produce wrong output. - if self.dcp_world_size > 1 and self.cp_kv_cache_interleave_size > 1: - raise NotImplementedError( - "DCP sparse indexer currently supports only " - f"cp_kv_cache_interleave_size=1 (got " - f"{self.cp_kv_cache_interleave_size})." - ) # NOTE(Chen):an estimated max size of flattened_kv. Need to double check. self.max_prefill_buffer_size = get_max_prefill_buffer_size(self.vllm_config) self.num_speculative_tokens = (