Skip to content

[fix] Update patch to track mindie changes #863

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
Infinite666 merged 1 commit into from
Mar 25, 2026
Merged

[fix] Update patch to track mindie changes #863

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1 change: 0 additions & 1 deletion docs/source/index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,6 @@ Paper list:
getting-started/quickstart_vllm
getting-started/quickstart_vllm_ascend
getting-started/quickstart_sglang
getting-started/quickstart_mindie_llm
getting-started/kv_cache_calculator
:::

Expand Down
9 changes: 4 additions & 5 deletions ucm/integration/mindie/patch/prefix_cache_plugin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,13 +60,12 @@ def hash_combine(seed, token_id):


class PrefixCachePlugin(Plugin):
def __init__(self, generator_backend, kvcache_settings, infer_context, output_filter, plugin_data_param, **kwargs):
def __init__(self, generator_backend, kvcache_settings, infer_context, plugin_data_param, **kwargs):
super().__init__()
self.generator_backend = generator_backend
self.model_wrapper = self.generator_backend.model_wrapper
self.kvcache_settings = kvcache_settings
self.infer_context = infer_context
self.output_filter = output_filter
self.plugin_data_param = plugin_data_param
self.model_name = self.generator_backend.model_name
self.sp_size = self.infer_context.spcp_parallel_info.sp_size
Expand Down Expand Up @@ -180,10 +179,10 @@ def model_inputs_update(self, model_inputs, input_metadata, sampling_metadata, c
f'#batchsize: {batch_size}, '
f'#batched-tokens: {input_metadata.total_seq_num}, '
f'#local cached-tokens: {local_matched_token_num}, '
f'#local cache hit rate: {round(local_cache_hit_rate, 3)}%, '
f'#local cached hit rate: {round(local_cache_hit_rate, 3)}%, '
f'#remote cached-tokens: {remote_matched_token_num}, '
f'#remote cache hit rate: {round(remote_cache_hit_rate, 3)}%, '
f'#cache hit rate: {round(local_cache_hit_rate + remote_cache_hit_rate, 3)}%')
f'#remote cached hit rate: {round(remote_cache_hit_rate, 3)}%, '
f'#cached hit rate: {round(local_cache_hit_rate + remote_cache_hit_rate, 3)}%')
print_log(self.rank, logger.info, f'Prefix Cache Global Reporter: '
f'#total prefill tokens: {self.total_token_num}, '
f'#total local matched tokens: {self.total_local_matched_token_num}, '
Expand Down
Loading