Skip to content

[None][feat] Support Glm4MoeForCausalLM #8256

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 17 commits into
base: main
Choose a base branch
from
Open

[None][feat] Support Glm4MoeForCausalLM #8256

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
17 commits
Select commit Hold shift + click to select a range
bd27665
ckpt
Oct 5, 2025
55ccb91
ckpt
dmtri35 Oct 6, 2025
235cf76
proper o_proj bias fix
dmtri35 Oct 6, 2025
ed930b9
revert bias hack
dmtri35 Oct 6, 2025
96a892d
revert unnecessary changes
dmtri35 Oct 6, 2025
0406f8a
ckpt
dmtri35 Oct 6, 2025
552b07a
Air ckpt
dmtri35 Oct 8, 2025
4a8a711
turn off a few kernel fusions
dmtri35 Oct 9, 2025
dae845b
working mtp
dmtri35 Oct 9, 2025
72a7ee7
fix mtp init
dmtri35 Oct 10, 2025
cc13c24
remove load_weights exception
dmtri35 Oct 13, 2025
95fe5ed
make begin and end thinking tokens variable
dmtri35 Oct 13, 2025
798939c
lint
dmtri35 Oct 14, 2025
706cad0
fix typo
dmtri35 Oct 15, 2025
dce80a9
resolve comments
dmtri35 Oct 18, 2025
9372c6e
revert passing in aux_stream
dmtri35 Oct 19, 2025
cd8d19e
add test
dmtri35 Oct 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions tensorrt_llm/_torch/models/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@
from .modeling_exaone4 import Exaone4ForCausalLM
from .modeling_gemma3 import Gemma3ForCausalLM
from .modeling_gemma3vl import Gemma3VLM
from .modeling_glm import Glm4MoeForCausalLM
from .modeling_gpt_oss import GptOssForCausalLM
from .modeling_hunyuan_dense import HunYuanDenseV1ForCausalLM
from .modeling_hunyuan_moe import HunYuanMoEV1ForCausalLM
Expand Down Expand Up @@ -70,6 +71,7 @@
"Qwen3NextForCausalLM",
"GptOssForCausalLM",
"SeedOssForCausalLM",
"Glm4MoeForCausalLM",
]

if transformers.__version__ >= "4.45.1":
Expand Down
Loading