{"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/async-request-trt-llm","entry":"async_request_trt_llm","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":11,"n_papers_ran":7,"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":3,"n_samples_fingerprinted":0,"n_places":11,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"unverified":4},"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","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,"code_sha256_prefix":"f0b0f51ad4ed00c9","mcp_get_code":{"code_sha256":"f0b0f51ad4ed00c9"}},{"arxiv_id":"2606.06302","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":true,"code_sha256_prefix":"f0b0f51ad4ed00c9","mcp_get_code":{"code_sha256":"f0b0f51ad4ed00c9"}},{"arxiv_id":"2605.08305","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,"code_sha256_prefix":"f273b25928123734","mcp_get_code":{"code_sha256":"f273b25928123734"}},{"arxiv_id":"2602.10718","paper":"/paper/arxiv-2602-10718","title":"SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"meituan-longcat/SGLang-FluentLLM","path":"python/sglang/bench_serving.py","file_url":"https://github.com/meituan-longcat/SGLang-FluentLLM/blob/HEAD/python/sglang/bench_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":"d5b639e0aaac30f5","mcp_get_code":{"code_sha256":"d5b639e0aaac30f5"}},{"arxiv_id":"2602.07223","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":true,"code_sha256_prefix":"f0b0f51ad4ed00c9","mcp_get_code":{"code_sha256":"f0b0f51ad4ed00c9"}},{"arxiv_id":"2601.20309","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8b9f8649ded1d025","mcp_get_code":{"code_sha256":"8b9f8649ded1d025"}},{"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/backend_request_func.py","file_url":"https://github.com/LLMServe/WarmServe/blob/HEAD/vllm-0.6.3.post1/benchmarks/backend_request_func.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":"31b4648baccb4d32","mcp_get_code":{"code_sha256":"31b4648baccb4d32"}},{"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/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":true,"code_sha256_prefix":"fa581ebc13cb414d","mcp_get_code":{"code_sha256":"fa581ebc13cb414d"}},{"arxiv_id":"2406.19215","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,"code_sha256_prefix":"fa581ebc13cb414d","mcp_get_code":{"code_sha256":"fa581ebc13cb414d"}},{"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/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,"code_sha256_prefix":"fa581ebc13cb414d","mcp_get_code":{"code_sha256":"fa581ebc13cb414d"}},{"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/backend_request_func.py","file_url":"https://github.com/hku-netexplo-lab/QSpec/blob/HEAD/benchmarks/backend_request_func.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":"7e1c24433ee7d75d","mcp_get_code":{"code_sha256":"7e1c24433ee7d75d"}}]}