Update get_expert_mapping to include self parameter (#33525)

Signed-off-by: Borushiki <38628261+Otsutsukii@users.noreply.github.com>

Update get_expert_mapping to include self parameter (#33525)
Signed-off-by: Borushiki <38628261+Otsutsukii@users.noreply.github.com>
b398e5c8 · Borushiki · GitHub · 78061ef5 · b398e5c8
Unverified Commit b398e5c8 authored Feb 02, 2026 by Borushiki Committed by GitHub Feb 02, 2026
Hide whitespace changes
Inline Side-by-side

Showing with 1 addition and 0 deletions

vllm/model_executor/models/glm4_moe_lite.py vllm/model_executor/models/glm4_moe_lite.py +1 -0

No files found.
--- a/vllm/model_executor/models/glm4_moe_lite.py
+++ b/vllm/model_executor/models/glm4_moe_lite.py
@@ -617,6 +617,7 @@ class Glm4MoeLiteForCausalLM(
        # Params for weights, fp8 weight scales, fp8 activation scales
        # (param_name, weight_name, expert_id, shard_id)
        return SharedFusedMoE.make_expert_params_mapping(
+            self,
            ckpt_gate_proj_name="gate_proj",
            ckpt_down_proj_name="down_proj",
            ckpt_up_proj_name="up_proj",