[Model] Use upstream GLM-5.3 and Qwen4-Exp configs and processor (#57387)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Harry Mellor
2026-10-02 02:25:18 +00:00
committed by GitHub
co-authored by Claude Opus 5
parent 866f02db8a
commit e3cae8d2ac
36 changed files with 366 additions and 2385 deletions
@@ -15,11 +15,11 @@ from types import SimpleNamespace
import pytest
import torch
from torch import nn
from transformers import Glm5NextTextConfig
from vllm.model_executor import parameter
from vllm.model_executor.layers import linear
from vllm.models.glm5next.common import model as glm_model
from vllm.transformers_utils.configs.glm5_next import Glm5NextTextConfig
HIDDEN, INTERMEDIATE, TP_SIZE = 8, 16, 2