Papers › AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

1 Jun 2023arXiv:2306.00978archive 2025-07-28

Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, Song Han

Large language models (LLMs) have transformed numerous AI applications. On-device LLM is becoming increasingly important: running LLMs locally on edge devices can reduce the cloud computing cost and protect users' privacy. However, the astronomical model size and the limited hardware resource pose significant deployment challenges. We propose Activation-aware Weight Quantization (AWQ), a hardware-friendly approach for LLM low-bit weight-only quantization. AWQ finds that not all weights in an LLM are equally important. Protecting only 1% salient weights can greatly reduce quantization error. To identify salient weight channels, we should refer to the activation distribution, not weights. To avoid the hardware-inefficient mix-precision quantization, we mathematically derive that scaling up the salient channels can reduce the quantization error. AWQ employs an equivalent transformation to scale the salient weight channels to protect them. The scale is determined by collecting the activation statistics offline. AWQ does not rely on any backpropagation or reconstruction, so it generalizes to different domains and modalities without overfitting the calibration set. AWQ outperforms existing work on various language modeling and domain-specific benchmarks (coding and math). Thanks to better generalization, it achieves excellent quantization performance for instruction-tuned LMs and, for the first time, multi-modal LMs. Alongside AWQ, we implement TinyChat, an efficient and flexible inference framework tailored for 4-bit on-device LLM/VLMs. With kernel fusion and platform-aware weight packing, TinyChat offers more than 3x speedup over the Huggingface FP16 implementation on both desktop and mobile GPUs. It also democratizes the deployment of the 70B Llama-2 model on mobile GPUs.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 18 code samples harvested from 4 repositories linked to this paper: 16 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 9 ran (2 with no instrument failure; 7 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 3 ran (1 with no instrument failure; 2 where Syntology's instrument failed); found in paper text by Syntology: 6 samples from 2 repositories, 4 ran (3 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 9 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

internlm/lmdeploy officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 9 samples, 9 ran (7 instrument-failed) · 0 unverified report
mit-han-lab/llm-awq officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Radio: Rate-Distortion Optimization for Large Language Model Compression (arXiv:2505.03031; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
nvidia/tensorrt-llm officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EnergyLens: Predictive Energy-Aware Exploration for Multi-GPU LLM Inference Optimization (arXiv:2605.14249; that paper's own run record: 6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
vllm-project/vllm officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning how to Forget: Fine-tuning for Long-Context Sparse Attention (arXiv:2608.19920; that paper's own run record: 21 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 5 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
bentoml/openllm mentioned on GitHubApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SqueezeLLM: Dense-and-Sparse Quantization (arXiv:2306.07629; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
casper-hansen/autoawq mentioned on GitHubpytorchMITSyntology: not harvested report
efficient-large-model/vila mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Scaling Vision Pre-Training to 4K Resolution (arXiv:2503.19903; that paper's own run record: 11 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
nvlabs/vila mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Scaling Vision Pre-Training to 4K Resolution (arXiv:2503.19903; that paper's own run record: 11 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
qwenlm/qwen2-vl mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution (arXiv:2409.12191; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
rasmith/vllm mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Efficient Memory Management for Large Language Model Serving with PagedAttention (arXiv:2309.06180; that paper's own run record: 28 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 5 honoured, 1 violated, 6 with no contract checked; 16 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
vectorch-ai/scalellm mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers (arXiv:2210.17323; that paper's own run record: 5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
xvyaward/qeft mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

18 samples harvested: 16 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
10ran · our draft was wrong
5ran
2unverified

Licence: 4 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

internlm/lmdeploy official repository 9 samples, 9 ran (7 instrument-failed) · 0 unverified
check_vl_llm lmdeploy/archs.py ran Apache-2.0 (permissive) · 2bf6c00c566b801c · report fixture: signature backend:str/0/str, config:dict/0/? · returned bool · level recorded 2026-09-24
compile_response_format lmdeploy/_guided_decoding.py ran Apache-2.0 (permissive) · 77ce2711c2f8950d · report fixture: signature compiler:MockCompiler/0/?, response_format:dict/0/? · returned str · level recorded 2026-09-24
get_text in 18 papers lmdeploy/model.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 7004ae9213140ec9 · report fixture: signature content:str/0/str · returned str · level recorded 2026-09-24
to_json in 5 papers lmdeploy/deepseek_v32_encoding.py ran · our draft was wrong Apache-2.0 (permissive) · c8ad433b6fe18d53 · report fixture: signature value:dict/0/? · returned str · level recorded 2026-09-24
to_json in 5 papers lmdeploy/deepseek_v4_encoding.py ran · our draft was wrong Apache-2.0 (permissive) · ee1294cf4de7d8c0 · report fixture: signature value:dict/0/? · returned str · level recorded 2026-09-24
tool_calls_from_openai_format lmdeploy/deepseek_v32_encoding.py ran · our draft was wrong Apache-2.0 (permissive) · e9281cecc545ad6f · report fixture: signature tool_calls:list/1/dict · returned list · level recorded 2026-09-24
tool_calls_from_openai_format lmdeploy/deepseek_v4_encoding.py ran · our draft was wrong Apache-2.0 (permissive) · 8b8cee237b9dc9d0 · report fixture: signature tool_calls:list/1/dict · returned list · level recorded 2026-09-24
tools_from_openai_format lmdeploy/deepseek_v32_encoding.py ran · our draft was wrong Apache-2.0 (permissive) · aa8d2113d1ab432e · report fixture: signature tools:list/1/dict · returned list · level recorded 2026-09-24
tools_from_openai_format lmdeploy/deepseek_v4_encoding.py ran · our draft was wrong Apache-2.0 (permissive) · a2584d89f3a50342 · report fixture: signature tools:list/1/dict · returned list · level recorded 2026-09-24
xvyaward/qeft community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
Quantizer in 10 papers qeft/quant.py ran · metamorphic tier: deterministic MIT (permissive) · 5608d56b0c71e653 · report fixture: returned Quantizer · level recorded 2026-09-22
quantize in 70 papers
census: 8 implementations from 11 papers, 6 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 3 of 3, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 0, kind float, dtype float32 · arg 3: rank 0, kind float, dtype float32 · arg 4: rank 0, kind float, dtype float32 · arg 5: rank 0, kind float, dtype float32
qeft/quant.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · a166c4b79b21b60a · report fixture: signature x:Tensor/2/float, scale:Tensor/0/float, zero:Tensor/0/float, minq:Tensor/0/float, maxq:Tensor/0/float · returned Tensor · level recorded 2026-09-22
quantize_efficient qeft/quant.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · 749e1b68c68b3203 · report fixture: signature x_round:Tensor/2/float, scale:Tensor/0/float, zero:Tensor/0/float, minq:Tensor/0/float, maxq:Tensor/0/float · returned Tensor · level recorded 2026-09-22
ggerganov/llama.cpp found in paper text by Syntology 5 samples, 3 ran (1 instrument-failed) · 2 unverified
get_base_tensor_name convert_lora_to_gguf.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 2b23d02a693ab3d2 · report fixture: signature lora_tensor_name:str/0/str · returned str · level recorded 2026-09-25
get_model_architecture conversion/base.py ran MIT (permissive) · a160a507db9a1d7a · report fixture: signature hparams:dict/0/?, model_type:int/0/int · returned str · level recorded 2026-09-26
split_str_to_n_bytes convert_hf_to_gguf.py ran · honoured contract MIT (permissive) · 084d06902aa98802 · report fixture: signature split_str:str/0/str · returned int · level recorded 2026-09-26
handle_metadata in 5 papers convert_llama_ggml_to_gguf.py unverified MIT (permissive) here; the stored copy is pointer only · cc924525c5e81162 · report
load_hparams_from_hf convert_lora_to_gguf.py unverified MIT (permissive) · e26587a77ee23aa1 · report
turboderp/exllama found in paper text by Syntology 1 sample, 1 ran (0 instrument-failed) · 0 unverified
timer in 24 papers example_alt_generator.py ran MIT (permissive) · 0339808d73c4cc66 · report fixture: signature func:callable/0/? · returned tuple · level recorded 2026-09-26

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for AWQ (graph method: AWQ). 3 bricks; individually on a fixture: 3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. Quantizer entry · level 1 · ran · 5608d56b0c71e653
  2. quantize helper · level 1 · ran · our draft was wrong · a166c4b79b21b60a
  3. quantize_efficient helper · level 1 · ran · our draft was wrong · 749e1b68c68b3203

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2306.00978") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Autonomous DrivingCloud ComputingCommon Sense ReasoningLanguage ModelingLanguage ModellingMathQuantization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections