{"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/split-tensor-along-last-dim","entry":"split_tensor_along_last_dim","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":12,"n_papers_ran":11,"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":8,"n_samples_ran":7,"n_samples_fingerprinted":1,"n_places":13,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":4,"unverified":1},"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":"2506.18841","paper":"/paper/longwriter-zero-mastering-ultra-long-text","title":"LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning","date":"2025-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/longwriter","path":"train/patch/modeling_chatglm.py","file_url":"https://github.com/thudm/longwriter/blob/HEAD/train/patch/modeling_chatglm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d7e378ee7899fbde","mcp_get_code":{"code_sha256":"d7e378ee7899fbde"}},{"arxiv_id":"2502.20766","paper":"/paper/flexprefill-a-context-aware-sparse-attention","title":"FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference","date":"2025-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/FlexPrefill","path":"flex_prefill/modules/glm/glm_self_attention_foward.py","file_url":"https://github.com/bytedance/FlexPrefill/blob/HEAD/flex_prefill/modules/glm/glm_self_attention_foward.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":"08b693a1068fa690","mcp_get_code":{"code_sha256":"08b693a1068fa690"}},{"arxiv_id":"2410.03577","paper":"/paper/look-twice-before-you-answer-memory-space","title":"Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models","date":"2024-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"1zhou-Wang/MemVR","path":"modeling/modeling_chatglm.py","file_url":"https://github.com/1zhou-Wang/MemVR/blob/HEAD/modeling/modeling_chatglm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d7e378ee7899fbde","mcp_get_code":{"code_sha256":"d7e378ee7899fbde"}},{"arxiv_id":"2408.10943","paper":"/paper/sysbench-can-large-language-models-follow","title":"SysBench: Can Large Language Models Follow System Messages?","date":"2024-08-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pku-baichuan-mlsystemlab/sysbench","path":"attenscore/modeling_chatglm.py","file_url":"https://github.com/pku-baichuan-mlsystemlab/sysbench/blob/HEAD/attenscore/modeling_chatglm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ffda302a67750064","mcp_get_code":{"code_sha256":"ffda302a67750064"}},{"arxiv_id":"2406.11257","paper":"/paper/excp-extreme-llm-checkpoint-compression-via","title":"ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gaffey/excp","path":"LMtrainer/mpu/utils.py","file_url":"https://github.com/gaffey/excp/blob/HEAD/LMtrainer/mpu/utils.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":"ff0731adadbb3e8f","mcp_get_code":{"code_sha256":"ff0731adadbb3e8f"}},{"arxiv_id":"2405.14297","paper":"/paper/dynamic-mixture-of-experts-an-auto-tuning","title":"Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lins-lab/dynmoe","path":"DeepSpeed-0.9.5/deepspeed/compression/basic_layer.py","file_url":"https://github.com/lins-lab/dynmoe/blob/HEAD/DeepSpeed-0.9.5/deepspeed/compression/basic_layer.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":"09c070245728e6e2","mcp_get_code":{"code_sha256":"09c070245728e6e2"}},{"arxiv_id":"2404.15159","paper":"/paper/mixlora-enhancing-large-language-models-fine","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mikecovlee/mLoRA","path":"mlora/models/modeling_chatglm.py","file_url":"https://github.com/mikecovlee/mLoRA/blob/HEAD/mlora/models/modeling_chatglm.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":"9281708eb4cf9161","mcp_get_code":{"code_sha256":"9281708eb4cf9161"}},{"arxiv_id":"2402.11809","paper":"/paper/generation-meets-verification-accelerating","title":"Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cteant/space","path":"src/models/modeling_chatglm.py","file_url":"https://github.com/cteant/space/blob/HEAD/src/models/modeling_chatglm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d7e378ee7899fbde","mcp_get_code":{"code_sha256":"d7e378ee7899fbde"}},{"arxiv_id":"2401.18058","paper":"/paper/longalign-a-recipe-for-long-context-alignment","title":"LongAlign: A Recipe for Long Context Alignment of Large Language Models","date":"2024-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/longalign","path":"modeling_chatglm.py","file_url":"https://github.com/thudm/longalign/blob/HEAD/modeling_chatglm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d7e378ee7899fbde","mcp_get_code":{"code_sha256":"d7e378ee7899fbde"}},{"arxiv_id":"2311.18445","paper":"/paper/vtimellm-empower-llm-to-grasp-video-moments","title":"VTimeLLM: Empower LLM to Grasp Video Moments","date":"2023-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huangb23/vtimellm","path":"vtimellm/model/chatglm/modeling_chatglm.py","file_url":"https://github.com/huangb23/vtimellm/blob/HEAD/vtimellm/model/chatglm/modeling_chatglm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d7e378ee7899fbde","mcp_get_code":{"code_sha256":"d7e378ee7899fbde"}},{"arxiv_id":"2307.13528","paper":"/paper/factool-factuality-detection-in-generative-ai","title":"FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios","date":"2023-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"freedomintelligence/sdak","path":"code/workers/modeling_chatglm.py","file_url":"https://github.com/freedomintelligence/sdak/blob/HEAD/code/workers/modeling_chatglm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d7e378ee7899fbde","mcp_get_code":{"code_sha256":"d7e378ee7899fbde"}},{"arxiv_id":"1909.08053","paper":"/paper/megatron-lm-training-multi-billion-parameter","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","date":"2019-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/fairscale","path":"fairscale/nn/model_parallel/layers.py","file_url":"https://github.com/facebookresearch/fairscale/blob/HEAD/fairscale/nn/model_parallel/layers.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"787ffed12fc28a46","mcp_get_code":{"code_sha256":"787ffed12fc28a46"}},{"arxiv_id":"1909.08053","paper":"/paper/megatron-lm-training-multi-billion-parameter","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","date":"2019-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qhduan/CPM-LM-TF2","path":"CPM-Generate/mpu/transformer.py","file_url":"https://github.com/qhduan/CPM-LM-TF2/blob/HEAD/CPM-Generate/mpu/transformer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c7a00a98e71fad14","mcp_get_code":{"code_sha256":"c7a00a98e71fad14"}}]}