Skip to content

Qwen3.5#2234

Open
wenbinc-Bin wants to merge 15 commits into
HabanaAI:aice/v1.22.0from
wenbinc-Bin:qwen3.5
Open

Qwen3.5#2234
wenbinc-Bin wants to merge 15 commits into
HabanaAI:aice/v1.22.0from
wenbinc-Bin:qwen3.5

Conversation

@wenbinc-Bin

@wenbinc-Bin wenbinc-Bin commented Feb 12, 2026

Copy link
Copy Markdown

Add Qwen3.5

cd vllm-fork/examples/offline_inference/basic
python basic.py --model Qwen/Qwen3.5-4B-Base --max-model-length 4096 --tp-size 1 --output-tokens 128

wenbinc-Bin and others added 5 commits February 11, 2026 06:51
vllm-project#34110
missing changes in
vllm/transformers_utils/model_arch_config_convertor.py
vllm/v1/spec_decode/eagle.py

Signed-off-by: Wenbin Chen <wenbin.chen@intel.com>
Signed-off-by: Wenbin Chen <wenbin.chen@intel.com>
Signed-off-by: Wenbin Chen <wenbin.chen@intel.com>
We don't support mtp so we can remove slicing.

Signed-off-by: Wenbin Chen <wenbin.chen@intel.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants