Zhenlin Wu

Results 7 comments of Zhenlin Wu

What I understand for the computation of recall is: Suppose we want to retrieve topk results for each query, there are N queries in total, then the recall rate should...

I see. Partially get your sentence. Another question is that how can we get the memory consumption results using ggnn to test on diferent datasets?

You mean run like ``` ./sift1m_multi --base_filename ../data/sift/sift_base.fvecs --query_filename ../data/sift/sift_query.fvecs --groundtruth_filename ../data/sift/sift_groundtruth.ivecs --gpu_ids="0" --v=4 ``` ?

Ok. So how to plug the graph contructed by HNSW for SONG to use for later searching. And, for graph data stored in bfsg.graph, does it stored in CSR format?...

Should I use the script shown in the docs https://docs.sglang.ai/backend/structured_outputs.html ``` import openai import os from sglang.test.test_utils import is_in_ci if is_in_ci(): from patch import launch_server_cmd else: from sglang.utils import launch_server_cmd...

Thank you. Currently, does the open-sourced xgrammer include scripts for the two benchmarking experiments (1. speed of masking logits and 2. end-to-end evaluation for the LLM inference engine efficiency in...

Hi, I have problems in installing libgoogle-glog-dev and libunwind-dev ![image](https://github.com/cgtuebingen/ggnn/assets/104770161/fd499650-9b4d-4c8f-8daf-3c7786e082ec) What should I do?