A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
Update GLM-4.5 Doc transformers version (#25830)
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Yuxuan Zhang committed
Sep 28, 2025 at 20:05 UTC
b1ded114b976b0fa4445565d235b23e64a4dc737
4 files changed
+7
-5
docs/features/tool_calling.md
+4
-2
@@ -323,8 +323,10 @@ Flags: `--tool-call-parser longcat`
323
324
Supported models:
325
326
-* `ZhipuAI/GLM-4.5`
327
-* `ZhipuAI/GLM-4.5-Air`
326
+* `zai-org/GLM-4.5`
327
+* `zai-org/GLM-4.5-Air`
328
+* `zai-org/GLM-4.6`
329
+* `zai-org/GLM-4.6-Air`
330
331
Flags: `--tool-call-parser glm45`
332
docs/models/supported_models.md
+1
-1
@@ -367,7 +367,7 @@ th {
367
| `Gemma3nForCausalLM` | Gemma 3n | `google/gemma-3n-E2B-it`, `google/gemma-3n-E4B-it`, etc. | | | ✅︎ |
368
| `GlmForCausalLM` | GLM-4 | `zai-org/glm-4-9b-chat-hf`, etc. | ✅︎ | ✅︎ | ✅︎ |
369
| `Glm4ForCausalLM` | GLM-4-0414 | `zai-org/GLM-4-32B-0414`, etc. | ✅︎ | ✅︎ | ✅︎ |
370
-| `Glm4MoeForCausalLM` | GLM-4.5 | `zai-org/GLM-4.5`, etc. | ✅︎ | ✅︎ | ✅︎ |
370
+| `Glm4MoeForCausalLM` | GLM-4.5, GLM-4.6 | `zai-org/GLM-4.5`, etc. | ✅︎ | ✅︎ | ✅︎ |
371
| `GPT2LMHeadModel` | GPT-2 | `gpt2`, `gpt2-xl`, etc. | | ✅︎ | ✅︎ |
372
| `GPTBigCodeForCausalLM` | StarCoder, SantaCoder, WizardCoder | `bigcode/starcoder`, `bigcode/gpt_bigcode-santacoder`, `WizardLM/WizardCoder-15B-V1.0`, etc. | ✅︎ | ✅︎ | ✅︎ |
373
| `GPTJForCausalLM` | GPT-J | `EleutherAI/gpt-j-6b`, `nomic-ai/gpt4all-j`, etc. | | ✅︎ | ✅︎ |
tests/models/registry.py
+1
-1
@@ -642,7 +642,7 @@ _SPECULATIVE_DECODING_EXAMPLE_MODELS = {
642
speculative_model="baidu/ERNIE-4.5-21B-A3B-PT"),
643
"Glm4MoeMTPModel": _HfExamplesInfo("zai-org/GLM-4.5",
644
speculative_model="zai-org/GLM-4.5",
645
- min_transformers_version="4.54",
645
+ min_transformers_version="4.56",
646
is_available_online=False),
647
"LongCatFlashMTPModel": _HfExamplesInfo(
648
"meituan-longcat/LongCat-Flash-Chat",
vllm/model_executor/models/glm4_moe.py
+1
-1
@@ -21,7 +21,7 @@
21
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
22
# See the License for the specific language governing permissions and
23
# limitations under the License.
24
-"""Inference-only GLM-4.5 model compatible with HuggingFace weights."""
24
+"""Inference-only GLM-4.5, GLM-4.6 model compatible with HuggingFace weights."""
25
import typing
26
from collections.abc import Callable, Iterable
27
from itertools import islice