{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/sample-requests","entry":"sample_requests","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":7,"n_papers_ran":5,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":9,"n_samples_ran":6,"n_samples_fingerprinted":0,"n_places":10,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":6,"unverified":3},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2512.09472","paper":"/paper/arxiv-2512-09472","title":"WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"LLMServe/WarmServe","path":"vllm-0.6.3.post1/benchmarks/benchmark_prefix_caching.py","file_url":"https://github.com/LLMServe/WarmServe/blob/HEAD/vllm-0.6.3.post1/benchmarks/benchmark_prefix_caching.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a8de224d74e65256","mcp_get_code":{"code_sha256":"a8de224d74e65256"}},{"arxiv_id":"2410.00428","paper":"/paper/layerkv-optimizing-large-language-model","title":"LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management","date":"2024-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"intelligent-machine-learning/glake","path":"GLakeServe/benchmarks/benchmark_throughput.py","file_url":"https://github.com/intelligent-machine-learning/glake/blob/HEAD/GLakeServe/benchmarks/benchmark_throughput.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f55439b30be97107","mcp_get_code":{"code_sha256":"f55439b30be97107"}},{"arxiv_id":"2410.00428","paper":"/paper/layerkv-optimizing-large-language-model","title":"LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management","date":"2024-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"intelligent-machine-learning/glake","path":"GLakeServe/benchmarks/benchmark_serving.py","file_url":"https://github.com/intelligent-machine-learning/glake/blob/HEAD/GLakeServe/benchmarks/benchmark_serving.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8abfc7dfff3ebb06","mcp_get_code":{"code_sha256":"8abfc7dfff3ebb06"}},{"arxiv_id":"2405.16444","paper":"/paper/cacheblend-fast-large-language-model-serving","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","date":"2024-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YaoJiayi/CacheBlend","path":"vllm_blend/benchmarks/benchmark_throughput.py","file_url":"https://github.com/YaoJiayi/CacheBlend/blob/HEAD/vllm_blend/benchmarks/benchmark_throughput.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f55439b30be97107","mcp_get_code":{"code_sha256":"f55439b30be97107"}},{"arxiv_id":"2404.14527","paper":"/paper/melange-cost-efficient-large-language-model","title":"Mélange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tyler-griggs/melange-release","path":"melange/profiling/gpu-benchmark.py","file_url":"https://github.com/tyler-griggs/melange-release/blob/HEAD/melange/profiling/gpu-benchmark.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a26ac3e30c9d5c27","mcp_get_code":{"code_sha256":"a26ac3e30c9d5c27"}},{"arxiv_id":"2402.01869","paper":"/paper/apiserve-efficient-api-support-for-large","title":"InferCept: Efficient Intercept Support for Augmented Large Language Model Inference","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wuklab/infercept","path":"benchmarks/benchmark_api_serving.py","file_url":"https://github.com/wuklab/infercept/blob/HEAD/benchmarks/benchmark_api_serving.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"84a26133838eab27","mcp_get_code":{"code_sha256":"84a26133838eab27"}},{"arxiv_id":"2402.01869","paper":"/paper/apiserve-efficient-api-support-for-large","title":"InferCept: Efficient Intercept Support for Augmented Large Language Model Inference","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wuklab/infercept","path":"benchmarks/benchmark_serving.py","file_url":"https://github.com/wuklab/infercept/blob/HEAD/benchmarks/benchmark_serving.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f4e08ad9325905dc","mcp_get_code":{"code_sha256":"f4e08ad9325905dc"}},{"arxiv_id":"2402.01869","paper":"/paper/apiserve-efficient-api-support-for-large","title":"InferCept: Efficient Intercept Support for Augmented Large Language Model Inference","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wuklab/infercept","path":"benchmarks/benchmark_throughput.py","file_url":"https://github.com/wuklab/infercept/blob/HEAD/benchmarks/benchmark_throughput.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ed11039cd60ea03f","mcp_get_code":{"code_sha256":"ed11039cd60ea03f"}},{"arxiv_id":"2402.01799","paper":"/paper/faster-and-lighter-llms-a-survey-on-current","title":"Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nyunAI/Faster-LLM-Survey","path":"engine/vllm/benchmark_throughput.py","file_url":"https://github.com/nyunAI/Faster-LLM-Survey/blob/HEAD/engine/vllm/benchmark_throughput.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c1750e41106c5c23","mcp_get_code":{"code_sha256":"c1750e41106c5c23"}},{"arxiv_id":"2025.emnlp-main.240","paper":null,"title":"arXiv:2025.emnlp-main.240","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"hku-netexplo-lab/QSpec","path":"benchmarks/benchmark_guided.py","file_url":"https://github.com/hku-netexplo-lab/QSpec/blob/HEAD/benchmarks/benchmark_guided.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"277d25f29be90815","mcp_get_code":{"code_sha256":"277d25f29be90815"}}]}