JetBrains / ArcticInference Duplication

Intro

For duplication, we look at places in code where there are 6 or more lines of code that are exactly the same.
Before duplication is calculated, the code is cleaned to remove empty lines, comments, and frequently duplicated constructs such as imports.
You should aim at having as little as possible (<5%) of duplicated code as high-level of duplication can lead to maintenance difficulties, poor factoring, and logical contradictions.

Learn more...

Duplication Overall

9% duplication:

8,652 cleaned lines of cleaned code (without empty lines, comments, and frequently duplicated constructs such as imports)
791 duplicated lines

54 duplicates

dependency graphs: 2D graph | 3D graph | 3D graph (with duplicates)...

Duplication per Extension

Duplication per Component (primary)

Duplication Between Components (50+ lines)

Download: SVG DOT (open online Graphviz editor)

From Component --> To Component	Duplicated Lines	File Pairs	Details
arctic_inference (<1%) --> projects (14%)	76	2 file pairs	details...

Open 2D force graph... Open 3D force graph...

Show more details on duplication between components...

Longest Duplicates

The list of 50 longest duplicates.

See data for all 54 duplicates...

Size	#	Folders	Files	Lines	Code
30	x 2	arctic_inference/dynasor arctic_inference/dynasor	evaluator.py evaluator.py	425:458 (4%) 466:499 (4%)	view
23	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	arctic_speculator.py arctic_speculator.py	295:321 (3%) 723:749 (3%)	view
20	x 2	arctic_inference/dynasor arctic_inference/dynasor	evaluator.py evaluator.py	368:387 (3%) 465:484 (3%)	view
19	x 2	arctic_inference/dynasor arctic_inference/dynasor	evaluator.py evaluator.py	369:387 (2%) 425:443 (2%)	view
18	x 2	projects/swiftkv projects/ulysses	offline_inference_swiftkv.py offline_inference_ulysses.py	23:44 (90%) 28:49 (75%)	view
16	x 2	projects/spec_dec projects/ulysses	offline_inference_spec_dec.py offline_inference_ulysses.py	36:53 (48%) 26:43 (66%)	view
15	x 2	projects/spec_dec projects/swiftkv	offline_inference_spec_dec.py offline_inference_swiftkv.py	38:53 (45%) 23:38 (75%)	view
13	x 2	arctic_inference/dynasor projects/dynasor	openai_server.py naive_client.py	335:348 (5%) 141:154 (12%)	view
12	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	arctic_speculator.py arctic_speculator.py	377:392 (1%) 859:874 (1%)	view
11	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	arctic_speculator.py arctic_speculator.py	360:371 (1%) 833:843 (1%)	view
11	x 2	arctic_inference/dynasor arctic_inference/dynasor	evaluator.py evaluator.py	403:417 (1%) 485:499 (1%)	view
11	x 2	arctic_inference/dynasor arctic_inference/dynasor	evaluator.py evaluator.py	403:417 (1%) 444:458 (1%)	view
10	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	arctic_speculator.py arctic_speculator.py	218:228 (1%) 578:588 (1%)	view
10	x 2	benchmark/embedding benchmark/embedding	benchmark.py benchmark_http.py	261:274 (4%) 173:186 (4%)	view
10	x 2	arctic_inference/vllm/swiftkv arctic_inference/vllm/swiftkv	llama_swiftkv.py llama_swiftkv.py	221:232 (1%) 285:296 (1%)	view
9	x 2	arctic_inference/dynasor projects/dynasor	openai_server.py openai_client.py	51:61 (3%) 24:34 (11%)	view
9	x 2	csrc/custom_ops csrc/custom_ops	quant_utils.cuh quant_utils.cuh	111:120 (1%) 396:405 (1%)	view
9	x 2	arctic_inference/dynasor arctic_inference/dynasor	cot.py entropy.py	42:50 (6%) 163:171 (9%)	view
9	x 2	benchmark/embedding benchmark/embedding	benchmark.py benchmark_http.py	308:316 (3%) 216:224 (3%)	view
9	x 2	csrc/custom_ops csrc/custom_ops	quant_utils.cuh quant_utils.cuh	157:166 (1%) 448:457 (1%)	view
9	x 2	arctic_inference/dynasor arctic_inference/dynasor	entropy.py evaluator.py	108:117 (9%) 753:762 (1%)	view
9	x 2	arctic_inference/dynasor projects/dynasor	openai_server.py naive_client.py	142:163 (3%) 44:66 (8%)	view
8	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	arctic_speculator.py arctic_speculator.py	826:833 (1%) 847:854 (1%)	view
8	x 2	benchmark/embedding benchmark/embedding	benchmark.py benchmark_http.py	337:344 (3%) 243:250 (3%)	view
8	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	arctic_speculator.py arctic_speculator.py	351:359 (1%) 814:822 (1%)	view
8	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	arctic_speculator.py arctic_speculator.py	283:291 (1%) 704:712 (1%)	view
8	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	arctic_speculator.py arctic_speculator.py	156:164 (1%) 448:456 (1%)	view
8	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	arctic_speculator.py arctic_speculator.py	166:173 (1%) 458:465 (1%)	view
7	x 2	benchmark/embedding benchmark/embedding	benchmark_http.py benchmark_http.py	81:87 (2%) 115:121 (2%)	view
7	x 2	benchmark/embedding benchmark/embedding	benchmark.py benchmark_http.py	378:384 (2%) 285:291 (2%)	view
7	x 2	benchmark/embedding benchmark/embedding	benchmark.py benchmark_http.py	59:65 (2%) 19:25 (2%)	view
7	x 2	arctic_inference/vllm arctic_inference/vllm	model_runner.py model_runner.py	501:507 (1%) 589:595 (1%)	view
7	x 2	benchmark/embedding benchmark/embedding	benchmark.py benchmark_http.py	68:85 (2%) 29:35 (2%)	view
7	x 2	arctic_inference/dynasor projects/dynasor	openai_server.py naive_client.py	173:179 (2%) 68:74 (6%)	view
7	x 2	arctic_inference/vllm/swiftkv arctic_inference/vllm/swiftkv	llama_swiftkv.py llama_swiftkv.py	538:544 (1%) 562:568 (1%)	view
7	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	arctic_speculator.py arctic_speculator.py	329:340 (<1%) 759:770 (<1%)	view
6	x 2	csrc/custom_ops csrc/custom_ops	quant_utils.cuh quant_utils.cuh	112:117 (1%) 449:454 (1%)	view
6	x 2	csrc/custom_ops csrc/custom_ops	quant_utils.cuh quant_utils.cuh	397:402 (1%) 449:454 (1%)	view
6	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	arctic_speculator.py arctic_speculator.py	845:850 (<1%) 854:859 (<1%)	view
6	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	arctic_speculator.py arctic_speculator.py	112:120 (<1%) 414:422 (<1%)	view
6	x 2	benchmark/embedding benchmark/embedding	benchmark.py benchmark_http.py	355:360 (2%) 261:266 (2%)	view
6	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	arctic_speculator.py arctic_speculator.py	360:365 (<1%) 824:829 (<1%)	view
6	x 2	csrc/custom_ops csrc/custom_ops	quant_utils.cuh quant_utils.cuh	158:163 (1%) 397:402 (1%)	view
6	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	arctic_speculator.py arctic_speculator.py	824:829 (<1%) 833:838 (<1%)	view
6	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	vocab_parallel_embedding.py vocab_parallel_embedding.py	223:228 (1%) 475:480 (1%)	view
6	x 2	arctic_inference/embedding arctic_inference/embedding	replica.py replica_manager.py	375:380 (2%) 425:430 (1%)	view
6	x 2	arctic_inference/vllm/swiftkv arctic_inference/vllm/swiftkv	llama_swiftkv.py llama_swiftkv.py	296:301 (<1%) 574:579 (<1%)	view
6	x 2	arctic_inference/vllm/swiftkv arctic_inference/vllm/swiftkv	llama_swiftkv.py llama_swiftkv.py	606:612 (<1%) 635:640 (<1%)	view
6	x 2	arctic_inference/suffix_decoding arctic_inference/suffix_decoding	cache.py cache.py	263:268 (4%) 272:277 (4%)	view
6	x 2	arctic_inference/vllm/spec_dec arctic_inference/vllm/spec_dec	arctic_speculator.py arctic_speculator.py	262:268 (<1%) 646:652 (<1%)	view