Skip to content

clean code & format for kvstar #241

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
hek14 merged 4 commits into from
Sep 29, 2025
Merged

clean code & format for kvstar #241

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
805bc04
Update multistep.py
saki-daisuki Sep 29, 2025
4ff65bf
Update utils.py
saki-daisuki Sep 29, 2025
e1fb9cf
Update offline_inference_kvstar.py
saki-daisuki Sep 29, 2025
0f05769
Update factory.py
saki-daisuki Sep 29, 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
14 changes: 10 additions & 4 deletions examples/offline_inference_kvstar.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ def setup_environment_variables():
os.environ["PYTHONHASHSEED"] = "123456"
os.environ["VLLM_TORCH_PROFILER_DIR"] = "./vllm_profile"


@contextlib.contextmanager
def build_llm_with_uc(module_path: str, name: str, model: str):
ktc = KVTransferConfig(
Expand All @@ -41,8 +42,8 @@ def build_llm_with_uc(module_path: str, name: str, model: str):
"local_window_sz": 2,
"sparse_ratio": 0.25,
"retrieval_stride": 8,
"blk_repre_dim_prune_ratio": 0.25, # 块表征维度裁剪
"blk_repre_inner_token_merge": 2 # 块内几个token融合成一个表征
"blk_repre_dim_prune_ratio": 0.25, # 块表征维度裁剪
"blk_repre_inner_token_merge": 2, # 块内几个token融合成一个表征
}
},
},
Expand Down Expand Up @@ -162,8 +163,13 @@ def main():

sampling_params = SamplingParams(temperature=0, top_k=1, max_tokens=300)

print_output(llm, prompts_prefill_more_than_2_full_blk, sampling_params, "first")
print_output(llm, prompts_prefill_more_than_2_full_blk, sampling_params, "second")
print_output(
llm, prompts_prefill_more_than_2_full_blk, sampling_params, "first"
)
print_output(
llm, prompts_prefill_more_than_2_full_blk, sampling_params, "second"
)


if __name__ == "__main__":
main()
4 changes: 3 additions & 1 deletion ucm/integration/vllm/ucm_sparse/factory.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,4 +49,6 @@ def create_sparse_method(
"KvComp", "ucm.sandbox.sparse.kvcomp.kvcomp", "KvComp"
)
UcmSparseFactory.register_sparse_method("GSA", "ucm.ucm_sparse.gsa", "GSA")
UcmSparseFactory.register_sparse_method("KVStarMultiStep", "ucm.ucm_sparse.kvstar.multistep", "KVStarMultiStep")
UcmSparseFactory.register_sparse_method(
"KVStarMultiStep", "ucm.ucm_sparse.kvstar.multistep", "KVStarMultiStep"
)
Loading