xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 03:54:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Model] Modify the gate implementation of glm4_moe (#22832)

Browse Source 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li 2025-08-14 20:28:50 +08:00 committed by GitHub
parent 829b9a62d0
commit 92ff41abea
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/models/supported_models.md
View File

@ -615,7 +615,7 @@ These models primarily accept the [`LLM.generate`](./generative_models.md#llmgen
| `Gemma3nForConditionalGeneration` | Gemma 3n | T + I + A | `google/gemma-3n-E2B-it`, `google/gemma-3n-E4B-it`, etc. | | | ✅︎ |
| `GLM4VForCausalLM`<sup>^</sup> | GLM-4V | T + I | `zai-org/glm-4v-9b`, `zai-org/cogagent-9b-20241220`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Glm4vForConditionalGeneration` | GLM-4.1V-Thinking | T + I<sup>E+</sup> + V<sup>E+</sup> | `zai-org/GLM-4.1V-9B-Thinking`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `Glm4vMoeForConditionalGeneration` | GLM-4.5V | T + I<sup>E+</sup> + V<sup>E+</sup> | `zai-org/GLM-4.5V`, etc. | | ✅︎ | ✅︎ |
| `Glm4vMoeForConditionalGeneration` | GLM-4.5V | T + I<sup>E+</sup> + V<sup>E+</sup> | `zai-org/GLM-4.5V`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `GraniteSpeechForConditionalGeneration` | Granite Speech | T + A | `ibm-granite/granite-speech-3.3-8b` | ✅︎ | ✅︎ | ✅︎ |
| `H2OVLChatModel` | H2OVL | T + I<sup>E+</sup> | `h2oai/h2ovl-mississippi-800m`, `h2oai/h2ovl-mississippi-2b`, etc. | | ✅︎ | ✅︎ |
| `Idefics3ForConditionalGeneration` | Idefics3 | T + I | `HuggingFaceM4/Idefics3-8B-Llama3`, etc. | ✅︎ | | ✅︎ |

20
vllm/model_executor/models/glm4_moe.py
View File

@ -41,7 +41,6 @@ from vllm.model_executor.layers.fused_moe import FusedMoE
from vllm.model_executor.layers.layernorm import RMSNorm
from vllm.model_executor.layers.linear import (MergedColumnParallelLinear,
QKVParallelLinear,
ReplicatedLinear,
RowParallelLinear)
from vllm.model_executor.layers.logits_processor import LogitsProcessor
from vllm.model_executor.layers.quantization import QuantizationConfig
@ -118,14 +117,15 @@ class Glm4MoE(nn.Module):
if config.hidden_act != "silu":
raise ValueError(f"Unsupported activation: {config.hidden_act}. "
"Only silu is supported for now.")
self.gate = ReplicatedLinear(config.hidden_size,
config.n_routed_experts,
bias=False,
quant_config=None,
params_dtype=torch.float32,
prefix=f"{prefix}.gate")
# NOTE In the transformers implementation, the gate isn't an nn.Linear,
# so we cannot use ReplicatedLinear here.
# See: https://github.com/huggingface/transformers/blob/v4.55.1/src/transformers/models/glm4_moe/modeling_glm4_moe.py#L260
self.gate = nn.Linear(
config.hidden_size,
config.n_routed_experts,
bias=False,
dtype=torch.float32,
)
self.gate.e_score_correction_bias = nn.Parameter(
torch.empty(config.n_routed_experts, dtype=torch.float32))
@ -181,7 +181,7 @@ class Glm4MoE(nn.Module):
if self.n_shared_experts is not None:
shared_output = self.shared_experts(hidden_states)
router_logits, _ = self.gate(hidden_states.to(dtype=torch.float32))
router_logits = self.gate(hidden_states.to(dtype=torch.float32))
final_hidden_states = self.experts(
hidden_states=hidden_states,
router_logits=router_logits) * self.routed_scaling_factor