From 4befc3140895b88c88522aec69416c73c3ea9eb5 Mon Sep 17 00:00:00 2001 From: shuwenn <47200617+alphabetc1@users.noreply.github.com> Date: Wed, 22 Apr 2026 10:48:45 +0800 Subject: [PATCH] fix: pass v_head_dim to MHA KV pools and validate MiMo HiCache geometry (#23173) Co-authored-by: Claude Opus 4.6 --- python/sglang/srt/model_executor/model_runner_kv_cache_mixin.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/python/sglang/srt/model_executor/model_runner_kv_cache_mixin.py b/python/sglang/srt/model_executor/model_runner_kv_cache_mixin.py index 74ce00c19..58658b12c 100644 --- a/python/sglang/srt/model_executor/model_runner_kv_cache_mixin.py +++ b/python/sglang/srt/model_executor/model_runner_kv_cache_mixin.py @@ -536,6 +536,7 @@ class ModelRunnerKVCacheMixin: get_attention_tp_size() ), head_dim=self.model_config.head_dim, + v_head_dim=self.model_config.v_head_dim, layer_num=self.num_effective_layers, device=self.device, enable_memory_saver=self.server_args.enable_memory_saver, @@ -555,6 +556,7 @@ class ModelRunnerKVCacheMixin: get_attention_tp_size() ), head_dim=self.model_config.head_dim, + v_head_dim=self.model_config.v_head_dim, layer_num=self.num_effective_layers, device=self.device, enable_memory_saver=self.server_args.enable_memory_saver,