minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

[Model] Add support for JetBrains' Mellum v2 code generation model (#27375)

Browse Source 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Jiminator <69131491+Jiminator@users.noreply.github.com>
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
This commit is contained in:
Madeesh Kannan
2026-07-13 22:54:38 -07:00
committed by GitHub
co-authored by gemini-code-assist[bot] Jiminator Alex Nails
parent 7e229e2a81
commit 702bddcee8
7 changed files with 706 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/kernels/fused_moe_triton/common_utils.py
+1
View File
@@ -84,6 +84,7 @@ def get_model_config(
"Qwen3VLMoeForConditionalGeneration",
"Qwen3_5MoeForConditionalGeneration",
"InternS2PreviewForConditionalGeneration",
"MellumForCausalLM",
]:
E = config.num_experts // ep_size
topk = config.num_experts_per_tok