Skip to content

update h config and add glm4.7 mtp test #4424

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

Merged
lvhan028 merged 13 commits into from
Apr 16, 2026
Merged

update h config and add glm4.7 mtp test #4424

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
c17c78b
update config h and add glm4.7 mtp test
Mar 18, 2026
c9d557f
update config
littlegy Mar 18, 2026
92fba62
fix benchmark test
littlegy Mar 18, 2026
5d7f415
fix gpt-oss args
littlegy Mar 19, 2026
11424c7
update
littlegy Mar 19, 2026
8671605
update vl test config
littlegy Mar 19, 2026
a2f1446
update bencmark test
littlegy Mar 19, 2026
1f87f65
Merge branch 'InternLM:main' into h_config
littlegy Apr 13, 2026
c6efe39
update config h and add qwen3.5 mtp
littlegy Apr 13, 2026
686cdc5
fix lint
littlegy Apr 13, 2026
45bcb87
update evaluate test
littlegy Apr 13, 2026
a954f86
update yml
littlegy Apr 13, 2026
b857e66
update
littlegy Apr 16, 2026
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
15 changes: 13 additions & 2 deletions autotest/config_ascend.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,12 @@ config:
Qwen/Qwen3-VL-30B-A3B-Instruct: 4
Qwen/Qwen3-VL-8B-Instruct: 2
Qwen/Qwen3-VL-32B-Instruct: 4
internlm/Intern-S1-Pro-BF16: 64

dp_ep:
internlm/Intern-S1-Pro-BF16:
dp: 64
ep: 64

pytorch_chat_model:
tp:
Expand All @@ -31,6 +37,10 @@ pytorch_chat_model:
- Qwen/Qwen3-32B
- Qwen/Qwen3-8B
- Qwen/Qwen3-0.6B
- internlm/Intern-S1-Pro-BF16

dp_ep:
- internlm/Intern-S1-Pro-BF16

pytorch_vl_model:
tp:
Expand All @@ -43,7 +53,6 @@ pytorch_vl_model:
- Qwen/Qwen3-VL-8B-Instruct
- Qwen/Qwen3-VL-32B-Instruct


pytorch_base_model:
tp:
- Qwen/Qwen3-0.6B
Expand All @@ -67,6 +76,7 @@ pytorch_quantization:
- Qwen/Qwen3-VL-30B-A3B-Instruct
- Qwen/Qwen3-VL-8B-Instruct
- Qwen/Qwen3-VL-32B-Instruct
- internlm/Intern-S1-Pro-BF16
no_kvint8:
- Qwen/Qwen3-30B-A3B
- Qwen/Qwen3-235B-A22B
Expand All @@ -81,8 +91,9 @@ pytorch_quantization:
- Qwen/Qwen3-VL-30B-A3B-Instruct
- Qwen/Qwen3-VL-8B-Instruct
- Qwen/Qwen3-VL-32B-Instruct
- internlm/Intern-S1-Pro-BF16

longtext_model:
longtext_benchmark_model:
- Qwen/Qwen3-30B-A3B

benchmark_model:
Expand Down
Loading
Loading