{"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/faster-and-lighter-llms-a-survey-on-current","title":"Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward","arxiv_id":"2402.01799","date":"2024-02-02","proceeding":null,"authors":["Arnav Chavan","Raghav Magazine","Shubham Kushwaha","Mérouane Debbah","Deepak Gupta"],"abstract":"Despite the impressive performance of LLMs, their widespread adoption faces challenges due to substantial computational and memory requirements during inference. Recent advancements in model compression and system-level optimization methods aim to enhance LLM inference. This survey offers an overview of these methods, emphasizing recent developments. Through experiments on LLaMA(/2)-7B, we evaluate various compression techniques, providing practical insights for efficient LLM deployment in a unified setting. The empirical analysis on LLaMA(/2)-7B highlights the effectiveness of these methods. Drawing from survey insights, we identify current limitations and discuss potential future directions to improve LLM inference efficiency. We release the codebase to reproduce the results presented in this paper at https://github.com/nyunAI/Faster-LLM-Survey","url_abs":"https://arxiv.org/abs/2402.01799v2","url_pdf":"https://arxiv.org/pdf/2402.01799v2.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":"faster-and-lighter-llms-a-survey-on-current","repo_url":"https://github.com/nyunai/faster-llm-survey","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"model-compression","task_name":"Model Compression"},{"task_slug":"survey","task_name":"Survey"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.01799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01799"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nyunai/faster-llm-survey","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/nyunAI/Faster-LLM-Survey","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"repositories":1}},"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":5,"samples":[{"code_sha256_prefix":"0692786f82b7affa","entry":"generate_torch","repo":"nyunai/faster-llm-survey","repo_kind":"official","path":"quant/awq/benchmark.py","file_url":"https://github.com/nyunai/faster-llm-survey/blob/HEAD/quant/awq/benchmark.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0692786f82b7affa"}},{"code_sha256_prefix":"c1750e41106c5c23","entry":"sample_requests","repo":"nyunAI/Faster-LLM-Survey","repo_kind":"official","path":"engine/vllm/benchmark_throughput.py","file_url":"https://github.com/nyunAI/Faster-LLM-Survey/blob/HEAD/engine/vllm/benchmark_throughput.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c1750e41106c5c23"}},{"code_sha256_prefix":"7338c4a1680894f6","entry":"load_data","repo":"nyunAI/Faster-LLM-Survey","repo_kind":"official","path":"quant/gptq/generation_speed.py","file_url":"https://github.com/nyunAI/Faster-LLM-Survey/blob/HEAD/quant/gptq/generation_speed.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7338c4a1680894f6"}},{"code_sha256_prefix":"f9de2270001387bd","entry":"load_data","repo":"nyunAI/Faster-LLM-Survey","repo_kind":"official","path":"quant/gptq/quant_with_alpaca.py","file_url":"https://github.com/nyunAI/Faster-LLM-Survey/blob/HEAD/quant/gptq/quant_with_alpaca.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f9de2270001387bd"}},{"code_sha256_prefix":"5a24809c17d18349","entry":"run_hf","repo":"nyunAI/Faster-LLM-Survey","repo_kind":"official","path":"engine/vllm/benchmark_throughput.py","file_url":"https://github.com/nyunAI/Faster-LLM-Survey/blob/HEAD/engine/vllm/benchmark_throughput.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5a24809c17d18349"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}