{"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/format-model-inspection","entry":"format_model_inspection","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":5,"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":1,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":0},"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/vllm/model_inspection.py","file_url":"https://github.com/Ravi-VK/SSR/blob/HEAD/vllm/vllm/model_inspection.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a696f84b9b36ab84","mcp_get_code":{"code_sha256":"a696f84b9b36ab84"}},{"arxiv_id":"2608.19920","paper":"/paper/arxiv-2608-19920","title":"Learning how to Forget: Fine-tuning for Long-Context Sparse Attention","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"vllm-project/vllm","path":"vllm/model_inspection.py","file_url":"https://github.com/vllm-project/vllm/blob/HEAD/vllm/model_inspection.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":"a696f84b9b36ab84","mcp_get_code":{"code_sha256":"a696f84b9b36ab84"}},{"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":"vllm/model_inspection.py","file_url":"https://github.com/platformxlab/vegas/blob/HEAD/vllm/model_inspection.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":"a696f84b9b36ab84","mcp_get_code":{"code_sha256":"a696f84b9b36ab84"}},{"arxiv_id":"2601.14327","paper":"/paper/arxiv-2601-14327","title":"Yuan3.0 Ultra: A Trillion-Parameter Enterprise-Oriented MoE LLM","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Yuan-lab-LLM/Yuan3.0-Ultra","path":"vllm/vllm/model_inspection.py","file_url":"https://github.com/Yuan-lab-LLM/Yuan3.0-Ultra/blob/HEAD/vllm/vllm/model_inspection.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":"a696f84b9b36ab84","mcp_get_code":{"code_sha256":"a696f84b9b36ab84"}},{"arxiv_id":"2309.06180","paper":"/paper/2309-06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","date":"2023-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rasmith/vllm","path":"vllm/model_inspection.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/model_inspection.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":"a696f84b9b36ab84","mcp_get_code":{"code_sha256":"a696f84b9b36ab84"}}]}