{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/async-request-tgi","entry":"async_request_tgi","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+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 = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":10,"n_papers_ran":10,"n_papers_ran_no_instrument_failure":9,"n_papers_ran_instrument_only":1,"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":7,"n_samples_ran":7,"n_samples_constructed":0,"n_samples_ran_checked":6,"n_samples_instrument":1,"n_samples_unverified":0,"n_samples_fingerprinted":0,"n_places":10,"n_places_pointer_only":7,"n_places_pointer_only_link_open":3,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":6,"unverified":0},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"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":"2608.20359","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2608-20359","title":"Self-Speculation for Faster Reasoning Models","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"Ravi-VK/SSR","path":"vllm/benchmarks/backend_request_func.py","file_url":"https://github.com/Ravi-VK/SSR/blob/HEAD/vllm/benchmarks/backend_request_func.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Ravi-VK/SSR when it was checked","code_sha256":"7ee13b8d142453c0","code_sha256_prefix":"7ee13b8d142453c0","mcp_get_code":{"code_sha256":"7ee13b8d142453c0"}},{"arxiv_id":"2606.06302","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-06302","title":"Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"aiha-lab/TANGRAM","path":"benchmarks/backend_request_func.py","file_url":"https://github.com/aiha-lab/TANGRAM/blob/HEAD/benchmarks/backend_request_func.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Ravi-VK/SSR, and GitHub detected no licence in that repository when it was checked","code_sha256":"7ee13b8d142453c0","code_sha256_prefix":"7ee13b8d142453c0","mcp_get_code":{"code_sha256":"7ee13b8d142453c0"}},{"arxiv_id":"2605.08305","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-08305","title":"LLMSYS-HPOBench: Hyperparameter Optimization Benchmark Suite for Real-World LLM Systems","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"ideas-labo/llmsys-hpobench","path":"sampler/Engine/vllm_sampler/benchmark/backend_request_func.py","file_url":"https://github.com/ideas-labo/llmsys-hpobench/blob/HEAD/sampler/Engine/vllm_sampler/benchmark/backend_request_func.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, ideas-labo/llmsys-hpobench, is not in the permissive set Syntology serves inline","code_sha256":"4eb1fa1a6a225d17","code_sha256_prefix":"4eb1fa1a6a225d17","mcp_get_code":{"code_sha256":"4eb1fa1a6a225d17"}},{"arxiv_id":"2602.07223","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-07223","title":"Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"platformxlab/vegas","path":"benchmarks/backend_request_func.py","file_url":"https://github.com/platformxlab/vegas/blob/HEAD/benchmarks/backend_request_func.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Ravi-VK/SSR, and GitHub detected no licence in that repository when it was checked","code_sha256":"7ee13b8d142453c0","code_sha256_prefix":"7ee13b8d142453c0","mcp_get_code":{"code_sha256":"7ee13b8d142453c0"}},{"arxiv_id":"2601.20309","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-20309","title":"SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Supercomputing-System-AI-Lab/SuperInfer","path":"benchmarks/backend_request_func.py","file_url":"https://github.com/Supercomputing-System-AI-Lab/SuperInfer/blob/HEAD/benchmarks/backend_request_func.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a6282cf6d8527c9e","code_sha256_prefix":"a6282cf6d8527c9e","mcp_get_code":{"code_sha256":"a6282cf6d8527c9e"}},{"arxiv_id":"2512.09472","arxiv_id_is_arxiv":true,"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/backend_request_func.py","file_url":"https://github.com/LLMServe/WarmServe/blob/HEAD/vllm-0.6.3.post1/benchmarks/backend_request_func.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"5fe8fe4d65cc1519","code_sha256_prefix":"5fe8fe4d65cc1519","mcp_get_code":{"code_sha256":"5fe8fe4d65cc1519"}},{"arxiv_id":"2410.00428","arxiv_id_is_arxiv":true,"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/backend_request_func.py","file_url":"https://github.com/intelligent-machine-learning/glake/blob/HEAD/GLakeServe/benchmarks/backend_request_func.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from YaoJiayi/CacheBlend, and GitHub detected no licence in that repository when it was checked","code_sha256":"23a62a462a38f854","code_sha256_prefix":"23a62a462a38f854","mcp_get_code":{"code_sha256":"23a62a462a38f854"}},{"arxiv_id":"2406.19215","arxiv_id_is_arxiv":true,"paper":"/paper/seakr-self-aware-knowledge-retrieval-for","title":"SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation","date":"2024-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-keg/seakr","path":"vllm_uncertainty/benchmarks/backend_request_func.py","file_url":"https://github.com/thu-keg/seakr/blob/HEAD/vllm_uncertainty/benchmarks/backend_request_func.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, thu-keg/seakr, is not in the permissive set Syntology serves inline","code_sha256":"a58940aabfd794f9","code_sha256_prefix":"a58940aabfd794f9","mcp_get_code":{"code_sha256":"a58940aabfd794f9"}},{"arxiv_id":"2405.16444","arxiv_id_is_arxiv":true,"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/backend_request_func.py","file_url":"https://github.com/YaoJiayi/CacheBlend/blob/HEAD/vllm_blend/benchmarks/backend_request_func.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, YaoJiayi/CacheBlend when it was checked","code_sha256":"23a62a462a38f854","code_sha256_prefix":"23a62a462a38f854","mcp_get_code":{"code_sha256":"23a62a462a38f854"}},{"arxiv_id":"2025.emnlp-main.240","arxiv_id_is_arxiv":false,"paper":null,"title":"ACL Anthology id 2025.emnlp-main.240","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"hku-netexplo-lab/QSpec","path":"benchmarks/backend_request_func.py","file_url":"https://github.com/hku-netexplo-lab/QSpec/blob/HEAD/benchmarks/backend_request_func.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"2d5a7161f18dfdfe","code_sha256_prefix":"2d5a7161f18dfdfe","mcp_get_code":{"code_sha256":"2d5a7161f18dfdfe"}}],"record_sha256":"d66d0a1733a248827de7a8b9dd5f994a03e5995d479d089145e91f4017d944d2","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}