{"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":"/paper/2309-06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","arxiv_id":"2309.06180","date":"2023-09-12","proceeding":null,"authors":["Woosuk Kwon","Zhuohan Li","Siyuan Zhuang","Ying Sheng","Lianmin Zheng","Cody Hao Yu","Joseph E. Gonzalez","Hao Zhang","Ion Stoica"],"abstract":"High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV cache) memory for each request is huge and grows and shrinks dynamically. When managed inefficiently, this memory can be significantly wasted by fragmentation and redundant duplication, limiting the batch size. To address this problem, we propose PagedAttention, an attention algorithm inspired by the classical virtual memory and paging techniques in operating systems. On top of it, we build vLLM, an LLM serving system that achieves (1) near-zero waste in KV cache memory and (2) flexible sharing of KV cache within and across requests to further reduce memory usage. Our evaluations show that vLLM improves the throughput of popular LLMs by 2-4$\\times$ with the same level of latency compared to the state-of-the-art systems, such as FasterTransformer and Orca. The improvement is more pronounced with longer sequences, larger models, and more complex decoding algorithms. vLLM's source code is publicly available at https://github.com/vllm-project/vllm","url_abs":"https://arxiv.org/abs/2309.06180v1","url_pdf":"https://arxiv.org/pdf/2309.06180v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"2309-06180","repo_url":"https://github.com/vllm-project/vllm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"2309-06180","repo_url":"https://github.com/ROCm/flash-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"2309-06180","repo_url":"https://github.com/adlik/vllm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"2309-06180","repo_url":"https://github.com/dao-ailab/flash-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"2309-06180","repo_url":"https://github.com/hazyresearch/flash-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"2309-06180","repo_url":"https://github.com/rasmith/vllm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"2309-06180","repo_url":"https://github.com/wuklab/infercept","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"management","task_name":"Management"}],"methods":[{"method_slug":"fragmentation","method_name":"Fragmentation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.06180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06180"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/vllm-project/vllm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wuklab/infercept","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dao-ailab/flash-attention","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ROCm/flash-attention","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rasmith/vllm","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hazyresearch/flash-attention","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/adlik/vllm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":22,"ran_fixture":1,"ran_honours":2,"unverified":11},"by_repo_kind":{"listed":{"samples":36,"ran":25,"repositories":3}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"5ec949977c334f87","entry":"apply_rotary_emb_torch","repo":"ROCm/flash-attention","repo_kind":"listed","path":"flash_attn/layers/rotary.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/flash_attn/layers/rotary.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5ec949977c334f87"}},{"code_sha256_prefix":"4afe00a5853d633f","entry":"attention_pytorch","repo":"ROCm/flash-attention","repo_kind":"listed","path":"flash_attn/cute/benchmark_flash_attention_fp8.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/flash_attn/cute/benchmark_flash_attention_fp8.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4afe00a5853d633f"}},{"code_sha256_prefix":"942ce4d7b0714c0a","entry":"attention_pytorch","repo":"ROCm/flash-attention","repo_kind":"listed","path":"benchmarks/benchmark_flash_attention.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/benchmarks/benchmark_flash_attention.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"942ce4d7b0714c0a"}},{"code_sha256_prefix":"cc628b160e090ba1","entry":"convert_blockmask","repo":"ROCm/flash-attention","repo_kind":"listed","path":"flash_attn/flash_blocksparse_attn_interface.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/flash_attn/flash_blocksparse_attn_interface.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"cc628b160e090ba1"}},{"code_sha256_prefix":"f29cb637db3ec374","entry":"efficiency","repo":"ROCm/flash-attention","repo_kind":"listed","path":"flash_attn/cute/benchmark_flash_attention_fp8.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/flash_attn/cute/benchmark_flash_attention_fp8.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f29cb637db3ec374"}},{"code_sha256_prefix":"b5de75d142329f03","entry":"efficiency","repo":"ROCm/flash-attention","repo_kind":"listed","path":"benchmarks/benchmark_flash_attention.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/benchmarks/benchmark_flash_attention.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b5de75d142329f03"}},{"code_sha256_prefix":"7541ce9614862680","entry":"flash_attn_qkvpacked_func","repo":"ROCm/flash-attention","repo_kind":"listed","path":"flash_attn/flash_attn_interface.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/flash_attn/flash_attn_interface.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"7541ce9614862680"}},{"code_sha256_prefix":"e73bdfbda28da341","entry":"flops","repo":"ROCm/flash-attention","repo_kind":"listed","path":"flash_attn/cute/benchmark_flash_attention_fp8.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/flash_attn/cute/benchmark_flash_attention_fp8.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e73bdfbda28da341"}},{"code_sha256_prefix":"8d5fb28ca2f46eb8","entry":"flops","repo":"ROCm/flash-attention","repo_kind":"listed","path":"benchmarks/benchmark_flash_attention.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/benchmarks/benchmark_flash_attention.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"8d5fb28ca2f46eb8"}},{"code_sha256_prefix":"a696f84b9b36ab84","entry":"format_model_inspection","repo":"rasmith/vllm","repo_kind":"listed","path":"vllm/model_inspection.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/model_inspection.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a696f84b9b36ab84"}},{"code_sha256_prefix":"9f09d0beacdd35d1","entry":"get_lock","repo":"adlik/vllm","repo_kind":"listed","path":"vllm/model_executor/weight_utils.py","file_url":"https://github.com/adlik/vllm/blob/HEAD/vllm/model_executor/weight_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9f09d0beacdd35d1"}},{"code_sha256_prefix":"13adeb89dc2bcd5c","entry":"init_logger","repo":"adlik/vllm","repo_kind":"listed","path":"vllm/logger.py","file_url":"https://github.com/adlik/vllm/blob/HEAD/vllm/logger.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"13adeb89dc2bcd5c"}},{"code_sha256_prefix":"1586b639a5abd0b0","entry":"init_to_zero","repo":"ROCm/flash-attention","repo_kind":"listed","path":"flash_attn/flash_attn_triton.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/flash_attn/flash_attn_triton.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1586b639a5abd0b0"}},{"code_sha256_prefix":"19ad2ccd82e378c1","entry":"maybe_contiguous","repo":"ROCm/flash-attention","repo_kind":"listed","path":"flash_attn/flash_attn_interface.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/flash_attn/flash_attn_interface.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"19ad2ccd82e378c1"}},{"code_sha256_prefix":"a39aa5bb3cefb4d0","entry":"maybe_convert_bool","repo":"rasmith/vllm","repo_kind":"listed","path":"vllm/envs.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/envs.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a39aa5bb3cefb4d0"}},{"code_sha256_prefix":"d11a43f137351612","entry":"maybe_convert_int","repo":"rasmith/vllm","repo_kind":"listed","path":"vllm/envs.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/envs.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d11a43f137351612"}},{"code_sha256_prefix":"a8cf6124094beaab","entry":"pad_input","repo":"ROCm/flash-attention","repo_kind":"listed","path":"flash_attn/bert_padding.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/flash_attn/bert_padding.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a8cf6124094beaab"}},{"code_sha256_prefix":"163292f43a3c861b","entry":"rotate_half","repo":"ROCm/flash-attention","repo_kind":"listed","path":"flash_attn/layers/rotary.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/flash_attn/layers/rotary.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"163292f43a3c861b"}},{"code_sha256_prefix":"a0595f1c95cacf06","entry":"round_multiple","repo":"ROCm/flash-attention","repo_kind":"listed","path":"flash_attn/flash_attn_interface.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/flash_attn/flash_attn_interface.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a0595f1c95cacf06"}},{"code_sha256_prefix":"bd5675c0d72d5295","entry":"run","repo":"rasmith/vllm","repo_kind":"listed","path":"vllm/collect_env.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/collect_env.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd5675c0d72d5295"}},{"code_sha256_prefix":"0b342669284f2be6","entry":"run_and_parse_first_match","repo":"rasmith/vllm","repo_kind":"listed","path":"vllm/collect_env.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/collect_env.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b342669284f2be6"}},{"code_sha256_prefix":"5ae630bfc3821b6e","entry":"run_and_read_all","repo":"rasmith/vllm","repo_kind":"listed","path":"vllm/collect_env.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/collect_env.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5ae630bfc3821b6e"}},{"code_sha256_prefix":"653b6f1bab40d0d2","entry":"str_dtype_to_torch_dtype","repo":"rasmith/vllm","repo_kind":"listed","path":"vllm/config/model.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/config/model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"653b6f1bab40d0d2"}},{"code_sha256_prefix":"d84093c20a0ed8fd","entry":"unpad_input","repo":"ROCm/flash-attention","repo_kind":"listed","path":"flash_attn/bert_padding.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/flash_attn/bert_padding.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d84093c20a0ed8fd"}},{"code_sha256_prefix":"62394c842aafb022","entry":"unpad_input_for_concatenated_sequences","repo":"ROCm/flash-attention","repo_kind":"listed","path":"flash_attn/bert_padding.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/flash_attn/bert_padding.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"62394c842aafb022"}},{"code_sha256_prefix":"a9519adef33152bb","entry":"convert_to_cudnn_type","repo":"ROCm/flash-attention","repo_kind":"listed","path":"hopper/benchmark_flash_attention_fp8.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/hopper/benchmark_flash_attention_fp8.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a9519adef33152bb"}},{"code_sha256_prefix":"c1aa2a7e052537ef","entry":"create_fp4_output_tensors","repo":"rasmith/vllm","repo_kind":"listed","path":"vllm/_custom_ops.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/_custom_ops.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c1aa2a7e052537ef"}},{"code_sha256_prefix":"5c034fc95116b35f","entry":"create_fp4_scale_tensor","repo":"rasmith/vllm","repo_kind":"listed","path":"vllm/_custom_ops.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/_custom_ops.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c034fc95116b35f"}},{"code_sha256_prefix":"58ebcd8dbefa010d","entry":"cudnn_spda_setup","repo":"ROCm/flash-attention","repo_kind":"listed","path":"hopper/benchmark_flash_attention_fp8.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/hopper/benchmark_flash_attention_fp8.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"58ebcd8dbefa010d"}},{"code_sha256_prefix":"982bc8603648cd4c","entry":"get_graph_partition_signature_patched","repo":"rasmith/vllm","repo_kind":"listed","path":"vllm/env_override.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/env_override.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"982bc8603648cd4c"}},{"code_sha256_prefix":"274e96c750b77b6d","entry":"get_served_model_name","repo":"rasmith/vllm","repo_kind":"listed","path":"vllm/config/model.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/config/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"274e96c750b77b6d"}},{"code_sha256_prefix":"d8ae3e91c8bc649b","entry":"maybe_convert_json_str_or_file","repo":"rasmith/vllm","repo_kind":"listed","path":"vllm/envs.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/envs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d8ae3e91c8bc649b"}},{"code_sha256_prefix":"2842ff1da04c998d","entry":"memory_plan_reuse_patched","repo":"rasmith/vllm","repo_kind":"listed","path":"vllm/env_override.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/env_override.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2842ff1da04c998d"}},{"code_sha256_prefix":"0ffca819d6ab93f9","entry":"prepare_hf_model_weights","repo":"adlik/vllm","repo_kind":"listed","path":"vllm/model_executor/weight_utils.py","file_url":"https://github.com/adlik/vllm/blob/HEAD/vllm/model_executor/weight_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0ffca819d6ab93f9"}},{"code_sha256_prefix":"556097b799045118","entry":"should_partition_patched","repo":"rasmith/vllm","repo_kind":"listed","path":"vllm/env_override.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/env_override.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"556097b799045118"}},{"code_sha256_prefix":"59912a58648c7c22","entry":"vocab_parallel_embedding","repo":"rasmith/vllm","repo_kind":"listed","path":"vllm/_custom_ops.py","file_url":"https://github.com/rasmith/vllm/blob/HEAD/vllm/_custom_ops.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59912a58648c7c22"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}