biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

feat: Complete LoRA support for MiniMaxM2 Fixes #32736 (#32763)

Browse Source 
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
david guan
2026-01-24 20:48:46 +08:00
committed by GitHub
parent 9ad7f89f55
commit bc0d291bfe
2 changed files with 11 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/models/supported_models.md
View File

@@ -422,7 +422,7 @@ th {
| `MiMoV2FlashForCausalLM` | MiMoV2Flash | `XiaomiMiMo/MiMo-V2-Flash`, etc. | ︎| ✅︎ |
| `MiniCPMForCausalLM` | MiniCPM | `openbmb/MiniCPM-2B-sft-bf16`, `openbmb/MiniCPM-2B-dpo-bf16`, `openbmb/MiniCPM-S-1B-sft`, etc. | ✅︎ | ✅︎ |
| `MiniCPM3ForCausalLM` | MiniCPM3 | `openbmb/MiniCPM3-4B`, etc. | ✅︎ | ✅︎ |
| `MiniMaxM2ForCausalLM` | MiniMax-M2, MiniMax-M2.1 |`MiniMaxAI/MiniMax-M2`, etc. | | ✅︎ |
| `MiniMaxM2ForCausalLM` | MiniMax-M2, MiniMax-M2.1 |`MiniMaxAI/MiniMax-M2`, etc. | ✅︎ | ✅︎ |
| `MistralForCausalLM` | Ministral-3, Mistral, Mistral-Instruct | `mistralai/Ministral-3-3B-Instruct-2512`, `mistralai/Mistral-7B-v0.1`, `mistralai/Mistral-7B-Instruct-v0.1`, etc. | ✅︎ | ✅︎ |
| `MistralLarge3ForCausalLM` | Mistral-Large-3-675B-Base-2512, Mistral-Large-3-675B-Instruct-2512 | `mistralai/Mistral-Large-3-675B-Base-2512`, `mistralai/Mistral-Large-3-675B-Instruct-2512`, etc. | ✅︎ | ✅︎ |
| `MixtralForCausalLM` | Mixtral-8x7B, Mixtral-8x7B-Instruct | `mistralai/Mixtral-8x7B-v0.1`, `mistralai/Mixtral-8x7B-Instruct-v0.1`, `mistral-community/Mixtral-8x22B-v0.1`, etc. | ✅︎ | ✅︎ |

12
vllm/model_executor/models/minimax_m2.py
View File

@@ -59,7 +59,7 @@ from vllm.model_executor.model_loader.weight_utils import (
)
from vllm.sequence import IntermediateTensors
from .interfaces import SupportsPP
from .interfaces import SupportsLoRA, SupportsPP
from .utils import (
AutoWeightsLoader,
PPMissingLayer,
@@ -484,7 +484,15 @@ class MiniMaxM2Model(nn.Module):
return loaded_params
class MiniMaxM2ForCausalLM(nn.Module, SupportsPP):
class MiniMaxM2ForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
packed_modules_mapping = {
"qkv_proj": [
"q_proj",
"k_proj",
"v_proj",
],
}
def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
super().__init__()
config = vllm_config.model_config.hf_config