volas

github.com/kaelzhang/volas

A Rust-backed, pandas-shaped DataFrame for live OHLCV pipelines: a broad trading-indicator set, incremental O(lookback) refresh on each new bar, and NumPy/Torch-ready output. This page is the project's reproducible benchmark report — regenerated from make benchmark on each release. See the repository for docs and installation.On this run, volas beats TA-Lib on 151 / 158 covered indicators by the default ratio, using the full coverage table below.

Benchmark report

OHLCV technical-indicator computation across libraries · 2026-10-05T12:54:53.556454+00:00 · Apple M1 (Virtual) · Python 3.12.10
Lower time is better; Perf shows the slowest candidate as 1.00× and each faster candidate as {slowest ÷ this}×.

pandaspandas_tastock_pandaspolarstalibvolas

Windowed live stream — 1m bars → 15m, bounded window (per-bar)

The live loop: fold a new 1-minute bar into a 15-minute series and refresh atr:14 over a bounded 30-bar window, every bar, for 20 000 bars. volas does this natively (a windowed, tf-aware frame that auto-compacts, so memory stays O(window + lookback)); the other libraries have no such primitive, so each is given a hand-written, non-lazy equivalent — a trimmed ring of the last window + max_lookback 15-minute bars, folded the same way and re-run through that library's ATR (never an O(n) recompute over all history). Times are per bar, amortized over the 20 000-bar stream (so volas's periodic compaction is included).

atr:14

Candidate	Mean	Median	OPS	rounds	Perf
volas	1.03 µs	1.12 µs	968,733	3	65.24×
talib	8.40 µs	8.30 µs	119,013	3	8.78×
polars	66.25 µs	63.39 µs	15,095	3	1.15×
pandas	72.14 µs	72.92 µs	13,861	3	1.00×

Append one new bar → updated indicator

A new bar arrives. volas / stock_pandas refresh their cached column incrementally (O(lookback)); the libraries with no indicator cache (pandas / pandas_ta / polars / talib) must recompute the series (O(n)). Every candidate is measured with the same round count so the rounds column is comparable.

atr:14

Candidate	Mean	Median	OPS	rounds	Perf
volas	696.2 ns	625.0 ns	1,436,431	500	1327.90×
talib	18.54 µs	14.87 µs	53,926	500	55.79×
polars	143.94 µs	120.40 µs	6,947	500	6.89×
pandas_ta	264.02 µs	141.38 µs	3,788	500	5.87×
stock_pandas	909.20 µs	793.02 µs	1,100	500	1.05×
pandas	1.07 ms	829.94 µs	935	500	1.00×

boll.upper

Candidate	Mean	Median	OPS	rounds	Perf
volas	2.05 µs	1.54 µs	488,415	500	424.52×
talib	14.18 µs	12.12 µs	70,515	500	53.99×
polars	177.87 µs	110.56 µs	5,622	500	5.92×
pandas	244.41 µs	191.50 µs	4,092	500	3.42×
stock_pandas	776.56 µs	598.87 µs	1,288	500	1.09×
pandas_ta	1.07 ms	654.60 µs	936	500	1.00×

ema:12

Candidate	Mean	Median	OPS	rounds	Perf
volas	695.7 ns	584.0 ns	1,437,405	500	995.08×
talib	7.61 µs	6.96 µs	131,365	500	83.51×
polars	56.50 µs	38.96 µs	17,699	500	14.92×
pandas	78.54 µs	45.04 µs	12,733	500	12.90×
pandas_ta	96.35 µs	60.85 µs	10,379	500	9.55×
stock_pandas	854.04 µs	581.12 µs	1,171	500	1.00×

ma:20

Candidate	Mean	Median	OPS	rounds	Perf
volas	2.57 µs	1.46 µs	388,427	500	342.32×
talib	6.79 µs	6.33 µs	147,296	500	78.82×
polars	80.37 µs	40.02 µs	12,442	500	12.48×
pandas	77.91 µs	56.15 µs	12,835	500	8.89×
pandas_ta	99.42 µs	66.48 µs	10,058	500	7.51×
stock_pandas	718.66 µs	499.27 µs	1,391	500	1.00×

macd

Candidate	Mean	Median	OPS	rounds	Perf
volas	922.1 ns	709.0 ns	1,084,488	500	793.67×
talib	26.25 µs	18.85 µs	38,102	500	29.85×
polars	121.26 µs	86.94 µs	8,246	500	6.47×
pandas	238.76 µs	170.87 µs	4,188	500	3.29×
pandas_ta	677.44 µs	439.17 µs	1,476	500	1.28×
stock_pandas	822.70 µs	562.71 µs	1,216	500	1.00×

macd.signal

Candidate	Mean	Median	OPS	rounds	Perf
volas	1.65 µs	834.0 ns	606,335	500	675.11×
talib	31.23 µs	32.08 µs	32,020	500	17.55×
polars	170.71 µs	145.25 µs	5,858	500	3.88×
pandas	267.23 µs	151.48 µs	3,742	500	3.72×
pandas_ta	544.88 µs	360.44 µs	1,835	500	1.56×
stock_pandas	829.34 µs	563.04 µs	1,206	500	1.00×

rsi:14

Candidate	Mean	Median	OPS	rounds	Perf
volas	1.30 µs	792.0 ns	771,399	500	784.93×
talib	25.44 µs	22.04 µs	39,311	500	28.21×
pandas_ta	103.91 µs	75.02 µs	9,624	500	8.29×
polars	786.03 µs	405.15 µs	1,272	500	1.53×
pandas	844.69 µs	564.35 µs	1,184	500	1.10×
stock_pandas	916.78 µs	621.67 µs	1,091	500	1.00×

willr:14

Candidate	Mean	Median	OPS	rounds	Perf
volas	2.19 µs	1.21 µs	456,401	500	224.39×
talib	13.32 µs	12.33 µs	75,091	500	22.00×
pandas_ta	169.95 µs	118.48 µs	5,884	500	2.29×
polars	145.57 µs	121.25 µs	6,869	500	2.24×
pandas	355.80 µs	271.29 µs	2,811	500	1.00×

Core DataFrame API (construct / slice / mask / assign / copy)

The data-handling plumbing a live system runs around every indicator call — frame construction, column access, row slicing, boolean masking, column assignment, copy — timed against pandas / polars. Not indicator math; the surrounding core APIs.

construct

Candidate	Mean	Median	OPS	rounds	Perf
volas	4.44 µs	4.29 µs	225,176	34633	11.91×
polars	23.37 µs	22.50 µs	42,781	913	2.27×
pandas	54.11 µs	51.13 µs	18,480	274	1.00×

copy

Candidate	Mean	Median	OPS	rounds	Perf
volas	392.9 ns	333.0 ns	2,544,910	24666	94.22×
polars	391.9 ns	375.0 ns	2,551,903	2043	83.67×
pandas	149.02 µs	31.37 µs	6,711	3792	1.00×

getcol

Candidate	Mean	Median	OPS	rounds	Perf
volas	335.9 ns	333.0 ns	2,977,093	58824	21.15×
polars	471.1 ns	458.0 ns	2,122,566	5137	15.38×
pandas	7.60 µs	7.04 µs	131,650	658	1.00×

mask

Candidate	Mean	Median	OPS	rounds	Perf
volas	11.38 µs	10.50 µs	87,844	1855	13.84×
pandas	98.18 µs	79.83 µs	10,185	317	1.82×
polars	155.75 µs	145.33 µs	6,420	75	1.00×

setitem

Candidate	Mean	Median	OPS	rounds	Perf
volas	1.15 µs	1.13 µs	869,972	2196	12.22×
pandas	8.23 µs	7.92 µs	121,450	1374	1.74×
polars	14.23 µs	13.75 µs	70,287	492	1.00×

slice

Candidate	Mean	Median	OPS	rounds	Perf
volas	3.50 µs	2.62 µs	286,082	8606	2.05×
pandas	7.80 µs	5.08 µs	128,186	3225	1.06×
polars	7.29 µs	5.38 µs	137,169	66	1.00×

Batch indicator computation

Compute the indicator over the whole series, across every library.

atr:14

Candidate	Mean	Median	OPS	rounds	Perf
volas	5.39 µs	4.50 µs	185,692	37325	138.79×
talib	18.74 µs	14.83 µs	53,368	30929	42.10×
stock_pandas	143.76 µs	105.75 µs	6,956	2782	5.91×
polars	214.89 µs	117.02 µs	4,654	1956	5.34×
pandas_ta	140.01 µs	120.71 µs	7,142	2253	5.17×
pandas	642.77 µs	624.54 µs	1,556	508	1.00×

boll.upper

Candidate	Mean	Median	OPS	rounds	Perf
volas	7.48 µs	6.17 µs	133,652	23646	99.44×
talib	13.98 µs	12.00 µs	71,544	35928	51.10×
polars	304.31 µs	93.46 µs	3,286	1818	6.56×
pandas	233.74 µs	182.88 µs	4,278	1195	3.35×
stock_pandas	224.88 µs	183.04 µs	4,447	3303	3.35×
pandas_ta	788.01 µs	613.15 µs	1,269	658	1.00×

ema:12

Candidate	Mean	Median	OPS	rounds	Perf
volas	10.65 µs	5.21 µs	93,927	24845	13.57×
talib	8.68 µs	7.00 µs	115,187	31704	10.10×
stock_pandas	58.30 µs	40.42 µs	17,153	7493	1.75×
pandas	67.02 µs	45.75 µs	14,920	3129	1.55×
polars	66.84 µs	47.83 µs	14,960	6013	1.48×
pandas_ta	100.44 µs	70.71 µs	9,956	1118	1.00×

hhv:10

Candidate	Mean	Median	OPS	rounds	Perf
volas	3.73 µs	3.21 µs	268,128	36037	17.67×
talib	7.40 µs	5.83 µs	135,172	30001	9.72×
polars	39.43 µs	30.04 µs	25,362	5903	1.89×
stock_pandas	61.34 µs	51.37 µs	16,302	5309	1.10×
pandas	68.99 µs	56.71 µs	14,496	2870	1.00×

llv:10

Candidate	Mean	Median	OPS	rounds	Perf
volas	4.50 µs	3.83 µs	221,999	41959	19.86×
talib	6.65 µs	5.83 µs	150,350	25210	13.05×
polars	48.31 µs	35.62 µs	20,699	3925	2.14×
stock_pandas	82.00 µs	51.63 µs	12,196	3104	1.47×
pandas	99.38 µs	76.15 µs	10,063	1880	1.00×

ma:20

Candidate	Mean	Median	OPS	rounds	Perf
volas	5.58 µs	4.42 µs	179,194	13606	18.04×
talib	9.72 µs	6.25 µs	102,861	28236	12.75×
polars	64.34 µs	40.25 µs	15,544	5153	1.98×
pandas	97.74 µs	57.58 µs	10,231	2587	1.38×
pandas_ta	93.92 µs	64.79 µs	10,647	2958	1.23×
stock_pandas	128.87 µs	79.67 µs	7,760	4575	1.00×

macd

Candidate	Mean	Median	OPS	rounds	Perf
volas	8.44 µs	7.00 µs	118,511	9837	57.11×
talib	25.87 µs	19.42 µs	38,658	23881	20.59×
stock_pandas	87.53 µs	57.46 µs	11,425	3447	6.96×
polars	142.30 µs	104.04 µs	7,027	457	3.84×
pandas	170.53 µs	120.98 µs	5,864	1110	3.30×
pandas_ta	528.66 µs	399.75 µs	1,892	952	1.00×

macd.signal

Candidate	Mean	Median	OPS	rounds	Perf
volas	14.73 µs	11.88 µs	67,896	9539	30.40×
talib	28.69 µs	20.67 µs	34,859	13529	17.47×
stock_pandas	102.01 µs	77.79 µs	9,803	3427	4.64×
polars	472.77 µs	134.21 µs	2,115	2081	2.69×
pandas	166.36 µs	147.25 µs	6,011	749	2.45×
pandas_ta	435.96 µs	360.96 µs	2,294	382	1.00×

rsi:14

Candidate	Mean	Median	OPS	rounds	Perf
volas	13.20 µs	12.08 µs	75,736	23392	40.52×
talib	14.50 µs	14.00 µs	68,977	37038	34.97×
stock_pandas	69.62 µs	59.79 µs	14,363	3719	8.19×
pandas_ta	79.75 µs	66.60 µs	12,539	2974	7.35×
polars	229.67 µs	187.33 µs	4,354	561	2.61×
pandas	535.44 µs	489.58 µs	1,868	571	1.00×

willr:14

Candidate	Mean	Median	OPS	rounds	Perf
volas	11.34 µs	10.00 µs	88,196	18032	26.58×
talib	14.55 µs	12.04 µs	68,707	26403	22.08×
pandas_ta	113.75 µs	101.58 µs	8,791	3128	2.62×
polars	3.78 ms	122.42 µs	265	49	2.17×
pandas	293.97 µs	265.83 µs	3,402	1226	1.00×

Full coverage — volas vs TA-Lib

Every indicator both volas and TA-Lib implement (the set the parity suite aligns), one row per indicator. The default volas vs TA-Lib column is the Tencent fixture; optional generated lengths and cached append refresh appear as additional ratio columns. Values > 1.00× mean volas is faster.

volas beats TA-Lib on 151 / 158 covered indicators by the default ratio (0 exactly even, 7 slower).

Indicator	volas	TA-Lib	volas vs TA-Lib (after append)	volas vs TA-Lib	volas vs TA-Lib (100)	volas vs TA-Lib (250)	volas vs TA-Lib (20000)
midpoint:14	7.62 µs	70.83 µs	67.33×	9.29×	n/a	n/a	n/a
cdl.stalledpattern	3.04 µs	22.12 µs	21.43×	7.28×	n/a	n/a	n/a
cdl.kicking	4.42 µs	29.58 µs	27.22×	6.70×	n/a	n/a	n/a
cdl.3starsinsouth	3.13 µs	16.58 µs	15.47×	5.31×	n/a	n/a	n/a
cdl.3whitesoldiers	6.17 µs	28.21 µs	24.82×	4.57×	n/a	n/a	n/a
minmax.min:30	3.71 µs	16.92 µs	11.58×	4.56×	n/a	n/a	n/a
cdl.upsidegap2crows	3.33 µs	14.88 µs	15.09×	4.46×	n/a	n/a	n/a
cdl.kickingbylength	6.58 µs	28.75 µs	26.58×	4.37×	n/a	n/a	n/a
cdl.morningstar	3.25 µs	14.13 µs	13.12×	4.35×	n/a	n/a	n/a
minmax.max:30	3.87 µs	16.83 µs	10.90×	4.34×	n/a	n/a	n/a
linearreg_intercept:14	3.17 µs	13.50 µs	13.54×	4.26×	n/a	n/a	n/a
cdl.thrusting	3.88 µs	16.13 µs	15.64×	4.16×	n/a	n/a	n/a
linearreg:14	3.50 µs	14.04 µs	13.05×	4.01×	n/a	n/a	n/a
cdl.haramicross	3.92 µs	15.50 µs	15.36×	3.96×	n/a	n/a	n/a
cdl.separatinglines	5.58 µs	22.00 µs	21.77×	3.94×	n/a	n/a	n/a
cdl.counterattack	4.50 µs	17.67 µs	16.93×	3.93×	n/a	n/a	n/a
tsf:14	3.62 µs	14.04 µs	11.66×	3.87×	n/a	n/a	n/a
minus_dm:14	3.12 µs	11.96 µs	20.55×	3.83×	n/a	n/a	n/a
plus_dm:14	3.17 µs	11.96 µs	18.53×	3.78×	n/a	n/a	n/a
linearreg_slope:14	3.15 µs	11.87 µs	11.92×	3.77×	n/a	n/a	n/a
cdl.marubozu	4.08 µs	15.25 µs	14.84×	3.73×	n/a	n/a	n/a
rocr:10	708.0 ns	2.54 µs	5.73×	3.59×	n/a	n/a	n/a
cdl.matchinglow	3.38 µs	12.04 µs	11.50×	3.57×	n/a	n/a	n/a
cdl.eveningstar	3.42 µs	12.13 µs	11.35×	3.55×	n/a	n/a	n/a
cdl.abandonedbaby	5.92 µs	19.96 µs	18.81×	3.37×	n/a	n/a	n/a
accbands:20	4.54 µs	15.00 µs	10.08×	3.30×	n/a	n/a	n/a
atr:14	4.17 µs	13.50 µs	23.23×	3.24×	n/a	n/a	n/a
cdl.ladderbottom	2.71 µs	8.67 µs	7.73×	3.20×	n/a	n/a	n/a
minmaxindex.max:30	6.67 µs	20.08 µs	35.09×	3.01×	n/a	n/a	n/a
natr:14	4.63 µs	13.42 µs	26.08×	2.90×	n/a	n/a	n/a
cdl.onneck	4.00 µs	11.17 µs	10.62×	2.79×	n/a	n/a	n/a
cdl.risefall3methods	8.96 µs	24.71 µs	21.94×	2.76×	n/a	n/a	n/a
cdl.sticksandwich	3.92 µs	10.79 µs	11.08×	2.76×	n/a	n/a	n/a
cdl.inneck	3.87 µs	10.58 µs	11.21×	2.73×	n/a	n/a	n/a
tema:30	5.25 µs	14.33 µs	27.52×	2.73×	n/a	n/a	n/a
medprice	566.7 ns	1.54 µs	3.70×	2.72×	n/a	n/a	n/a
accbands.lower:20	5.54 µs	15.00 µs	10.00×	2.71×	n/a	n/a	n/a
accbands.upper:20	5.54 µs	14.96 µs	10.67×	2.70×	n/a	n/a	n/a
cdl.identical3crows	7.29 µs	19.54 µs	18.16×	2.68×	n/a	n/a	n/a
linearreg_angle:14	12.79 µs	34.08 µs	30.30×	2.66×	n/a	n/a	n/a
cdl.advanceblock	11.33 µs	30.00 µs	25.63×	2.65×	n/a	n/a	n/a
cdl.dragonflydoji	4.42 µs	11.21 µs	10.58×	2.54×	n/a	n/a	n/a
cdl.unique3river	5.17 µs	13.08 µs	12.23×	2.53×	n/a	n/a	n/a
mom:10	595.8 ns	1.50 µs	3.36×	2.52×	n/a	n/a	n/a
trix:30	6.50 µs	16.17 µs	25.07×	2.49×	n/a	n/a	n/a
wclprice	687.5 ns	1.71 µs	4.55×	2.48×	n/a	n/a	n/a
macdfix	6.67 µs	16.29 µs	23.25×	2.44×	n/a	n/a	n/a
cdl.highwave	2.50 µs	6.04 µs	5.66×	2.42×	n/a	n/a	n/a
midprice:14	7.71 µs	18.62 µs	16.03×	2.42×	n/a	n/a	n/a
boll.middle	4.25 µs	10.25 µs	6.89×	2.41×	n/a	n/a	n/a
wma:30	2.44 µs	5.87 µs	4.03×	2.41×	n/a	n/a	n/a
ht_dcphase	196.96 µs	472.46 µs	436.12×	2.40×	n/a	n/a	n/a
ht_sine.sine	213.46 µs	510.17 µs	426.00×	2.39×	n/a	n/a	n/a
cdl.longline	5.21 µs	12.37 µs	12.93×	2.38×	n/a	n/a	n/a
avgprice	833.0 ns	1.96 µs	4.71×	2.35×	n/a	n/a	n/a
macd	6.83 µs	16.04 µs	25.05×	2.35×	n/a	n/a	n/a
ht_trendmode	241.79 µs	559.88 µs	430.02×	2.32×	n/a	n/a	n/a
ht_sine.leadsine	213.08 µs	489.17 µs	514.88×	2.30×	n/a	n/a	n/a
typprice	729.1 ns	1.67 µs	4.21×	2.29×	n/a	n/a	n/a
cdl.dojistar	5.21 µs	11.88 µs	11.76×	2.28×	n/a	n/a	n/a
cdl.invertedhammer	5.58 µs	12.67 µs	12.85×	2.27×	n/a	n/a	n/a
cci:14	10.42 µs	23.50 µs	18.80×	2.26×	n/a	n/a	n/a
dema:30	4.83 µs	10.83 µs	17.94×	2.24×	n/a	n/a	n/a
cdl.homingpigeon	3.17 µs	6.96 µs	6.88×	2.20×	n/a	n/a	n/a
minmaxindex.min:30	9.58 µs	20.29 µs	35.53×	2.12×	n/a	n/a	n/a
cdl.shortline	5.38 µs	11.33 µs	10.00×	2.11×	n/a	n/a	n/a
ultosc	8.29 µs	17.29 µs	9.90×	2.09×	n/a	n/a	n/a
cdl.mathold	9.75 µs	19.71 µs	18.01×	2.02×	n/a	n/a	n/a
cdl.tasukigap	4.67 µs	9.33 µs	9.09×	2.00×	n/a	n/a	n/a
cdl.gravestonedoji	5.62 µs	11.25 µs	10.96×	2.00×	n/a	n/a	n/a
cdl.harami	3.25 µs	6.50 µs	6.32×	2.00×	n/a	n/a	n/a
cdl.eveningdojistar	8.75 µs	17.42 µs	15.67×	1.99×	n/a	n/a	n/a
tr	1000.0 ns	1.96 µs	4.80×	1.96×	n/a	n/a	n/a
dx:14	8.58 µs	16.75 µs	28.80×	1.95×	n/a	n/a	n/a
boll.lower	5.50 µs	10.62 µs	6.86×	1.93×	n/a	n/a	n/a
cdl.gapsidesidewhite	5.25 µs	10.08 µs	10.25×	1.92×	n/a	n/a	n/a
cdl.spinningtop	2.71 µs	5.17 µs	5.16×	1.91×	n/a	n/a	n/a
cdl.3blackcrows	5.42 µs	10.29 µs	9.93×	1.90×	n/a	n/a	n/a
cdl.3inside	7.33 µs	13.92 µs	13.20×	1.90×	n/a	n/a	n/a
plus_di:14	7.42 µs	14.04 µs	22.60×	1.89×	n/a	n/a	n/a
beta:5@high,low	6.92 µs	12.71 µs	7.20×	1.84×	n/a	n/a	n/a
boll.upper	5.46 µs	9.87 µs	6.89×	1.81×	n/a	n/a	n/a
cdl.rickshawman	4.25 µs	7.67 µs	7.52×	1.80×	n/a	n/a	n/a
trima:30	4.17 µs	7.25 µs	4.97×	1.74×	n/a	n/a	n/a
cdl.concealbabyswall	6.21 µs	10.71 µs	10.19×	1.73×	n/a	n/a	n/a
cdl.closingmarubozu	4.33 µs	7.46 µs	7.46×	1.72×	n/a	n/a	n/a
cdl.doji	2.50 µs	4.21 µs	3.96×	1.68×	n/a	n/a	n/a
maxindex:30	6.71 µs	11.25 µs	19.65×	1.68×	n/a	n/a	n/a
cdl.morningdojistar	9.33 µs	15.62 µs	14.58×	1.67×	n/a	n/a	n/a
cdl.longleggeddoji	2.92 µs	4.87 µs	5.22×	1.67×	n/a	n/a	n/a
minus_di:14	7.71 µs	12.87 µs	22.67×	1.67×	n/a	n/a	n/a
cdl.belthold	4.17 µs	6.96 µs	6.73×	1.67×	n/a	n/a	n/a
cdl.takuri	5.08 µs	8.37 µs	8.00×	1.65×	n/a	n/a	n/a
aroon.up:14	6.08 µs	9.92 µs	9.00×	1.63×	3.72×	2.91×	1.61×
cdl.2crows	4.75 µs	7.62 µs	8.17×	1.61×	n/a	n/a	n/a
rocr100:10	1.61 µs	2.58 µs	5.33×	1.60×	n/a	n/a	n/a
rocp:10	1.60 µs	2.54 µs	5.25×	1.59×	n/a	n/a	n/a
roc:10	1.64 µs	2.58 µs	6.10×	1.58×	3.13×	2.78×	1.07×
ad	2.69 µs	4.12 µs	6.67×	1.53×	n/a	n/a	n/a
cdl.shootingstar	5.46 µs	8.29 µs	8.44×	1.52×	n/a	n/a	n/a
cdl.tristar	5.25 µs	7.92 µs	7.46×	1.51×	3.11×	2.30×	2.36×
macdfix.signal	10.83 µs	16.33 µs	26.40×	1.51×	n/a	n/a	n/a
aroon.down:14	6.79 µs	9.92 µs	9.19×	1.46×	3.36×	2.88×	1.58×
hhv:10	3.00 µs	4.33 µs	4.54×	1.44×	2.94×	2.45×	1.58×
macdext	10.04 µs	14.42 µs	7.78×	1.44×	n/a	n/a	n/a
macd.signal	10.83 µs	15.54 µs	24.46×	1.43×	n/a	n/a	n/a
cdl.piercing	3.29 µs	4.71 µs	4.68×	1.43×	n/a	n/a	n/a
macd.histogram	11.17 µs	15.63 µs	28.87×	1.40×	n/a	n/a	n/a
cdl.engulfing	3.17 µs	4.42 µs	4.19×	1.40×	n/a	n/a	n/a
macdfix.histogram	11.42 µs	15.92 µs	28.33×	1.39×	n/a	n/a	n/a
adx:14	11.54 µs	16.08 µs	24.18×	1.39×	n/a	n/a	n/a
cdl.xsidegap3methods	4.88 µs	6.79 µs	7.48×	1.39×	n/a	n/a	n/a
adxr:14	11.92 µs	16.46 µs	23.36×	1.38×	n/a	n/a	n/a
stoch.d	11.54 µs	15.83 µs	14.77×	1.37×	2.83×	2.07×	1.30×
cdl.3outside	3.00 µs	4.08 µs	4.12×	1.36×	n/a	n/a	n/a
minindex:30	9.79 µs	13.21 µs	20.67×	1.35×	n/a	n/a	n/a
sar	5.04 µs	6.75 µs	9.22×	1.34×	n/a	n/a	n/a
ma:20	3.96 µs	5.29 µs	4.13×	1.34×	n/a	n/a	n/a
sarext	5.29 µs	7.00 µs	9.39×	1.32×	n/a	n/a	n/a
adosc	5.29 µs	6.96 µs	9.44×	1.32×	n/a	n/a	n/a
bop	2.33 µs	3.04 µs	6.73×	1.30×	n/a	n/a	n/a
llv:10	3.67 µs	4.71 µs	4.18×	1.28×	n/a	n/a	n/a
cdl.darkcloudcover	3.42 µs	4.37 µs	4.24×	1.28×	n/a	n/a	n/a
stochf.k	9.33 µs	11.87 µs	11.96×	1.27×	n/a	n/a	n/a
obv	2.58 µs	3.21 µs	3.95×	1.24×	n/a	n/a	n/a
cdl.hikkakemod	9.08 µs	11.13 µs	10.77×	1.22×	n/a	n/a	n/a
cdl.3linestrike	5.12 µs	6.21 µs	5.89×	1.21×	2.85×	2.17×	1.24×
t3:5	5.71 µs	6.87 µs	11.79×	1.20×	n/a	n/a	n/a
cdl.hikkake	3.71 µs	4.46 µs	4.16×	1.20×	3.27×	2.53×	1.06×
ema:12	4.75 µs	5.71 µs	11.01×	1.20×	n/a	n/a	n/a
aroonosc:14	8.08 µs	9.54 µs	8.22×	1.18×	2.91×	2.26×	1.03×
var:5	4.46 µs	5.25 µs	4.57×	1.18×	n/a	n/a	n/a
stddev:5	5.04 µs	5.92 µs	6.00×	1.17×	n/a	n/a	n/a
stoch.k	13.50 µs	15.83 µs	14.71×	1.17×	n/a	n/a	n/a
kama:30	5.08 µs	5.92 µs	9.60×	1.16×	n/a	n/a	n/a
sum:30	4.46 µs	5.17 µs	3.34×	1.16×	n/a	n/a	n/a
cdl.breakaway	4.25 µs	4.87 µs	4.56×	1.15×	3.22×	2.36×	2.01×
stochf.d	10.42 µs	11.87 µs	11.04×	1.14×	2.81×	1.97×	1.20×
stochrsi.k	18.96 µs	21.58 µs	31.43×	1.14×	n/a	n/a	n/a
willr:14	9.04 µs	10.29 µs	9.77×	1.14×	n/a	n/a	n/a
stochrsi.d	19.83 µs	22.33 µs	29.18×	1.13×	1.93×	1.43×	1.12×
ht_trendline	111.58 µs	125.54 µs	132.00×	1.13×	n/a	n/a	n/a
ppo	10.21 µs	11.46 µs	6.16×	1.12×	n/a	n/a	n/a
cdl.hammer	8.54 µs	9.54 µs	9.08×	1.12×	n/a	n/a	n/a
rsi:14	11.12 µs	12.13 µs	22.01×	1.09×	n/a	n/a	n/a
mavp:2,30@close,periods	123.58 µs	133.42 µs	24.84×	1.08×	n/a	n/a	n/a
correl:30@high,low	6.54 µs	7.04 µs	3.28×	1.08×	n/a	n/a	n/a
cmo:14	12.08 µs	12.87 µs	21.66×	1.07×	n/a	n/a	n/a
macdext.signal	13.54 µs	13.92 µs	7.61×	1.03×	n/a	n/a	n/a
mfi:14	4.83 µs	4.96 µs	4.07×	1.03×	2.92×	2.14×	3.71×
mama	101.21 µs	102.58 µs	106.87×	1.01×	1.11×	1.02×	1.15×
mama.fama	108.42 µs	106.63 µs	117.73×	0.98×	n/a	n/a	n/a
ht_phasor.quadrature	102.54 µs	100.71 µs	132.06×	0.98×	n/a	n/a	n/a
apo	10.04 µs	9.79 µs	5.15×	0.98×	n/a	n/a	n/a
ht_phasor.inphase	103.17 µs	97.33 µs	125.30×	0.94×	n/a	n/a	n/a
macdext.histogram	15.54 µs	14.50 µs	7.80×	0.93×	n/a	n/a	n/a
ht_dcperiod	118.50 µs	106.08 µs	123.15×	0.90×	1.02×	0.94×	0.89×
cdl.hangingman	11.88 µs	9.33 µs	9.65×	0.79×	n/a	n/a	n/a

Generated by scripts/benchmark_report.py from pytest-benchmark output.