Add Mistral Large 3 support. (#14213)

Co-authored-by: elvischenv <219235043+elvischenv@users.noreply.github.com> Co-authored-by: Linda-Stadter <57756729+Linda-Stadter@users.noreply.github.com>
2025-12-04 20:00:05 +08:00
parent af35023e65
commit 8428078436
16 changed files with 1400 additions and 120 deletions
@@ -73,11 +73,17 @@ def get_model_config(
        "DeepseekV2ForCausalLM",
        "DeepseekV3ForCausalLM",
        "Glm4MoeForCausalLM",
+        "MistralLarge3ForCausalLM",
    ]:
        E = (config.n_routed_experts // ep_size) + (
            0
            if disable_shared_experts_fusion
-            or architecture not in ["DeepseekV3ForCausalLM", "Glm4MoeForCausalLM"]
+            or architecture
+            not in [
+                "DeepseekV3ForCausalLM",
+                "Glm4MoeForCausalLM",
+                "MistralLarge3ForCausalLM",
+            ]
            else 1
        )
        topk = config.num_experts_per_tok + (