L0 / SURFACE

Tanish Shah

Computer Engineering · Minor in Data Science · Mumbai

Engineer with a founder's bias.

Incoming call AI voice

Tanish's agent

Read transcript

Hi, this is Tanish's agent. He's not on the line, but I am. He builds the voice agents that make calls like this one, the automations behind them, and he's measured what happens on the GPU when a model answers. Stay on the line. Scroll down and I'll walk you through it.

L1 / VOICE Timescale · seconds

Voice

I run the agents that make outbound calls for a global fintech-education company.

Calling coverage, 9 to 59 countries.

Regions shown are indicative.

FIG. 1 · Calling coverage

Work · this layer

AI Intern, Marketing Automation & Growth

QuantInsti Quantitative Learning Pvt. Ltd., Mumbai

Jul 2026 to present

Make · LeadSquared CRM · OpenAI · Retell AI · Twilio · Vobiz · Claude Code

  1. Outbound voice agents

    • I own the Retell AI outbound calling agents on Twilio and Vobiz telephony.
    • I added social-engineering guardrails to 28 live agent prompts.
    • I fixed a silent failure in the 24-hour call-frequency guard.
    • I built timezone-aware regional routing and a callback scheduler, and expanded calling coverage from 9 to 59 countries.
    • I built a daily call-funnel report.
  2. Voice Agent Call QA Auditor

    CrewAI

    github.com/RedPillCoder1/voice-agent-call-qa-auditor
    • A CrewAI multi-agent system that audits voice-agent calls, built on synthetic call data.

This is one turn of one call.

  1. 01 Telephony Twilio / Vobiz Carries the call audio in and out.
  2. 02 Speech to text transcribe Turns the caller's audio into text.
  3. 03 LLM decide what to say Reads the conversation so far and writes the next line.
  4. 04 Text to speech speak Turns that line back into a voice.

back to the caller

FIG. 2 · Anatomy of one outbound turn
L2 / ORCHESTRATION Timescale · milliseconds

Orchestration

Behind every call and every email is a pipeline. I build them, ship them and pay for them.

Before QuantInsti

Real software for a real business.

Backend Automation Engineer Intern (sole technical hire)

AMAFHH Import and Export Pvt. Ltd., Mumbai

Jun 2025 to Sep 2025

FastAPI · Windows Server · Tally · Google Sheets

Google Sheets FastAPI XML Tally

  • Owned the architecture, build and deployment of a production backend (HTTPS, IP allowlisting, HMAC-SHA256 request auth).
  • Built a voucher pipeline from Google Sheets through FastAPI and XML into Tally, handling godown logic, conditional GST rules and a ±1% broker tolerance. It eliminated fulfilment errors on real transaction volume.
  • Brought back in Oct 2026 to build a multi-user delivery-challan web app (per-user login, GST calculation, print preview, challan history).

Work · this layer
QuantInsti, continued

  1. AI email engine, live on real leads

    • A two-stage LLM pipeline (strategist, then writer) that writes one persona-targeted nurture email per CRM lead webhook, at about $0.33 per email.
    • It ships through audit-driven releases.
    • I designed its core rule: a lead's personal data steers the message but never appears in it.
  2. Content engine

    Playwright · ffmpeg · AI voice

    • AI short-form reels produced through a code pipeline.
    • "The Desk" reached 2,300 views in under 48 hours against a 555-view account median. It became the account's best reel and now its reference format.
    • Designed from a 44-reel baseline and a 25-account study.
    • I also run an AI-assisted X replies programme and WhatsApp bulk campaigns.
  3. Cost and reliability

    • When the org hit its 300k-credit automation cap, I attributed spend per module and ranked the savings.
    • I built a gate that stops malformed LLM output from reaching the CRM.
    • I flagged security issues in live automation configs.
  1. I/O CRM lead webhook

    A new lead arrives from the CRM.

  2. LLM Strategist

    LLM. Reads the lead and decides what the email should say.

  3. LLM Writer

    LLM. Writes the email. The lead's details steer it but never appear in it.

  4. GATE Output gate

    Checks the output. Malformed output stops here.

  5. I/O CRM

    Receives one finished email per lead.

    one email per lead

A lead's personal data steers the message but never appears in it.

FIG. 3 · AI email engine, one lead · synthetic data
L3 / INSIDE THE MODEL Timescale · microseconds

Inside the model

A model will say anything. My job is making sure only valid output gets acted on.

Work · this layer

  1. Agentic Futures Trading Engine

    Groq · Llama 3.1 8B · Docker

    github.com/RedPillCoder1/trading-bot
    • Turns natural-language trade intent into Binance Futures orders.
    • A zero-trust validation layer blocks hallucinated parameters before any network call.
    • Result: zero invalid exchange requests in paper-trading tests.
  2. Autonomous Venture Lab

    FastAPI · Next.js · LLM agents · Monte Carlo

    autonomousventurelab.vercel.app
    • An AI startup-investment analyst.
    • A 4-agent LLM team (CEO, CFO, CMO, Critic) with schema-enforced JSON handoffs debates each venture.
    • Then 10,000 Monte Carlo simulations per request across 4 exit scenarios return a probabilistic verdict in under a second.
  3. 4-agent software team

    CrewAI · OpenAI Agents SDK

    • PM, Developer, Tester and Reviewer agents that turn a feature spec into tested, reviewed code.
Instruction

"short 0.01 BTC at market, 5x"

  1. t0 short
  2. t1 0
  3. t2 .
  4. t3 01
  5. t4 BTC
  6. t5 at
  7. t6 market
  8. t7 ,
  9. t8 5
  10. t9 x
Parsed, then validated
fieldvaluefromcheck
side SELL t0 ok
symbol BTCUSDT t4 ok
type MARKET t6 ok
quantity 0.01 t1 t2 t3 ok
leverage 500 t8 t9 out of range · blocked
exchange

blocked before any network call

FIG. 4 · Intent in, validated order out · Illustrative values · Attention shown is illustrative
L4 / SILICON Timescale · nanoseconds

The silicon

Every answer a model gives costs time on a GPU. I built a profiler that shows where it goes.

Flagship · open source

InferenceLens

Python · PyTorch · FastAPI · WebSocket · MPS

An open-source GPU-layer profiler for self-hosted LLMs. It covers the gap between LangSmith and NVIDIA Nsight, because neither shows per-layer GPU attribution.

It located 4x layer-level attention bottlenecks.

GPT-2 on Apple unified memory shows 33% p50 to p99 jitter. Llama 3.1 8B on a dedicated NVIDIA GPU, a model 64x larger, shows 7.8%.

GPT-2 · Apple unified memory

n = 153 · real requests · 25 Apr 2026

2026-04-25 03:43:44 · 0.3172 s · LOW · Healthy · VRAM as reported 8.36 MB 2026-04-25 03:47:17 · 0.4404 s · LOW · Healthy · VRAM as reported 8.36 MB 2026-04-25 03:31:21 · 0.5619 s · LOW · Healthy · VRAM as reported 8.36 MB 2026-04-25 03:49:48 · 0.6754 s · LOW · Healthy · VRAM as reported 8.36 MB 2026-04-25 03:45:32 · 0.7234 s · LOW · Healthy · VRAM as reported 8.36 MB 2026-04-25 03:53:52 · 0.7537 s · LOW · Healthy · VRAM as reported 8.36 MB 2026-04-25 03:14:27 · 0.9154 s · LOW · Healthy · VRAM as reported 16.36 MB 2026-04-25 03:43:27 · 0.9371 s · LOW · Healthy · VRAM as reported 24.36 MB 2026-04-25 03:45:24 · 0.9894 s · LOW · Healthy · VRAM as reported 24.36 MB 2026-04-25 03:32:57 · 1.0006 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 8.36 MB 2026-04-25 03:47:44 · 1.0481 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:30:15 · 1.0498 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:48:27 · 1.0519 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:47:52 · 1.0528 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:48:18 · 1.0531 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:47:09 · 1.0554 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:48:00 · 1.0554 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:42:50 · 1.0612 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:42:42 · 1.0615 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:47:26 · 1.0628 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:50:53 · 1.0631 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:44:45 · 1.0638 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:54:22 · 1.0657 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:48:45 · 1.0663 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:48:35 · 1.0670 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:51:19 · 1.0672 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:30:24 · 1.0673 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:48:53 · 1.0675 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:52:11 · 1.0681 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:41:48 · 1.0689 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:50:25 · 1.0692 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:51:37 · 1.0698 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:42:59 · 1.0702 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:42:32 · 1.0705 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:39:27 · 1.0710 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:50:43 · 1.0710 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:46:10 · 1.0713 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:43:35 · 1.0714 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:43:08 · 1.0719 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:51:02 · 1.0722 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:51:11 · 1.0725 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:26:37 · 1.0730 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:41:40 · 1.0737 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:39:18 · 1.0738 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:51:28 · 1.0738 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:52:29 · 1.0738 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:39:55 · 1.0747 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:52:56 · 1.0747 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:41:31 · 1.0749 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:42:23 · 1.0749 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:53:05 · 1.0752 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:49:02 · 1.0758 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:35:10 · 1.0759 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:52:20 · 1.0760 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:39:37 · 1.0774 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:47:34 · 1.0779 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:29:48 · 1.0791 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:43:17 · 1.0798 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:49:20 · 1.0801 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:41:13 · 1.0806 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:26:06 · 1.0813 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:54:02 · 1.0826 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:40:34 · 1.0827 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:39:46 · 1.0844 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:29:39 · 1.0849 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:51:54 · 1.0856 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:50:16 · 1.0862 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:29:56 · 1.0869 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:41:57 · 1.0869 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:35:21 · 1.0873 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:49:30 · 1.0893 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:42:14 · 1.0907 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:30:06 · 1.0909 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:45:50 · 1.0918 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:26:27 · 1.0920 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:44:05 · 1.0955 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:41:03 · 1.0956 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:33:54 · 1.0969 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:30:53 · 1.0974 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:40:13 · 1.0985 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:42:06 · 1.0990 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:48:09 · 1.0991 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:40:53 · 1.0994 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:26:17 · 1.0996 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:45:41 · 1.1002 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:34:13 · 1.1005 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:30:44 · 1.1009 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:31:02 · 1.1017 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:51:45 · 1.1021 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:40:43 · 1.1023 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:32:19 · 1.1045 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:34:04 · 1.1049 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:31:29 · 1.1053 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:46:19 · 1.1068 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:50:34 · 1.1073 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:32:10 · 1.1074 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:34:42 · 1.1104 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:40:23 · 1.1104 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:52:02 · 1.1120 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:47:01 · 1.1140 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:26:47 · 1.1146 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:40:04 · 1.1148 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:41:23 · 1.1155 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:53:43 · 1.1160 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:53:26 · 1.1169 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:49:39 · 1.1177 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:44:15 · 1.1231 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:50:07 · 1.1234 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:54:12 · 1.1245 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:35:30 · 1.1275 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:43:55 · 1.1282 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:27:16 · 1.1294 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:44:54 · 1.1296 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:32:28 · 1.1302 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:31:11 · 1.1304 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:31:38 · 1.1332 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:52:37 · 1.1367 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:53:34 · 1.1396 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:49:11 · 1.1406 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:34:52 · 1.1414 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:45:15 · 1.1437 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:25:55 · 1.1444 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:35:01 · 1.1452 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:46:00 · 1.1482 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:46:29 · 1.1491 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:44:36 · 1.1515 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:29:30 · 1.1532 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:39:08 · 1.1540 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:14:07 · 1.1542 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:45:04 · 1.1549 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:27:27 · 1.1550 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:32:48 · 1.1579 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:46:40 · 1.1718 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:25:43 · 1.1740 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:32:00 · 1.1830 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:52:46 · 1.1868 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:33:07 · 1.1914 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:14:41 · 1.1926 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 8.36 MB 2026-04-25 03:32:38 · 1.1936 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:44:25 · 1.1936 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:33:34 · 1.1978 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:29:19 · 1.2034 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:27:05 · 1.2040 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:33:16 · 1.2092 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:53:15 · 1.2355 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:46:51 · 1.2367 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:30:33 · 1.2470 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:33:44 · 1.2537 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:34:33 · 1.2891 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:49:57 · 1.3718 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:34:23 · 1.3808 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:33:25 · 1.4565 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:31:48 · 1.6107 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB

← 6 faster, below 0.8 s

2026-04-25 03:14:27 · 0.9154 s · LOW · Healthy · VRAM as reported 16.36 MB 2026-04-25 03:43:27 · 0.9371 s · LOW · Healthy · VRAM as reported 24.36 MB 2026-04-25 03:45:24 · 0.9894 s · LOW · Healthy · VRAM as reported 24.36 MB 2026-04-25 03:32:57 · 1.0006 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 8.36 MB 2026-04-25 03:47:44 · 1.0481 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:30:15 · 1.0498 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:48:27 · 1.0519 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:47:52 · 1.0528 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:48:18 · 1.0531 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:47:09 · 1.0554 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:48:00 · 1.0554 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:42:50 · 1.0612 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:42:42 · 1.0615 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:47:26 · 1.0628 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:50:53 · 1.0631 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:44:45 · 1.0638 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:54:22 · 1.0657 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:48:45 · 1.0663 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:48:35 · 1.0670 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:51:19 · 1.0672 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:30:24 · 1.0673 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:48:53 · 1.0675 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:52:11 · 1.0681 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:41:48 · 1.0689 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:50:25 · 1.0692 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:51:37 · 1.0698 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:42:59 · 1.0702 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:42:32 · 1.0705 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:39:27 · 1.0710 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:50:43 · 1.0710 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:46:10 · 1.0713 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:43:35 · 1.0714 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:43:08 · 1.0719 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:51:02 · 1.0722 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:51:11 · 1.0725 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:26:37 · 1.0730 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:41:40 · 1.0737 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:39:18 · 1.0738 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:51:28 · 1.0738 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:52:29 · 1.0738 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:39:55 · 1.0747 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:52:56 · 1.0747 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:41:31 · 1.0749 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:42:23 · 1.0749 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:53:05 · 1.0752 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:49:02 · 1.0758 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:35:10 · 1.0759 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:52:20 · 1.0760 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:39:37 · 1.0774 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:47:34 · 1.0779 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:29:48 · 1.0791 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:43:17 · 1.0798 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:49:20 · 1.0801 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:41:13 · 1.0806 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:26:06 · 1.0813 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:54:02 · 1.0826 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:40:34 · 1.0827 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:39:46 · 1.0844 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:29:39 · 1.0849 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:51:54 · 1.0856 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:50:16 · 1.0862 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:29:56 · 1.0869 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:41:57 · 1.0869 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:35:21 · 1.0873 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:49:30 · 1.0893 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:42:14 · 1.0907 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:30:06 · 1.0909 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:45:50 · 1.0918 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:26:27 · 1.0920 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:44:05 · 1.0955 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:41:03 · 1.0956 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:33:54 · 1.0969 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:30:53 · 1.0974 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:40:13 · 1.0985 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:42:06 · 1.0990 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:48:09 · 1.0991 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:40:53 · 1.0994 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:26:17 · 1.0996 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:45:41 · 1.1002 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:34:13 · 1.1005 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:30:44 · 1.1009 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:31:02 · 1.1017 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:51:45 · 1.1021 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:40:43 · 1.1023 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:32:19 · 1.1045 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:34:04 · 1.1049 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:31:29 · 1.1053 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:46:19 · 1.1068 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:50:34 · 1.1073 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:32:10 · 1.1074 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:34:42 · 1.1104 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:40:23 · 1.1104 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:52:02 · 1.1120 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:47:01 · 1.1140 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:26:47 · 1.1146 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:40:04 · 1.1148 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:41:23 · 1.1155 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:53:43 · 1.1160 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:53:26 · 1.1169 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:49:39 · 1.1177 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:44:15 · 1.1231 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:50:07 · 1.1234 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:54:12 · 1.1245 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:35:30 · 1.1275 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:43:55 · 1.1282 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:27:16 · 1.1294 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:44:54 · 1.1296 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:32:28 · 1.1302 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:31:11 · 1.1304 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:31:38 · 1.1332 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:52:37 · 1.1367 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:53:34 · 1.1396 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:49:11 · 1.1406 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:34:52 · 1.1414 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:45:15 · 1.1437 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:25:55 · 1.1444 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:35:01 · 1.1452 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:46:00 · 1.1482 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:46:29 · 1.1491 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:44:36 · 1.1515 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:29:30 · 1.1532 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:39:08 · 1.1540 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:14:07 · 1.1542 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:45:04 · 1.1549 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:27:27 · 1.1550 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:32:48 · 1.1579 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:46:40 · 1.1718 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:25:43 · 1.1740 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:32:00 · 1.1830 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:52:46 · 1.1868 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:33:07 · 1.1914 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:14:41 · 1.1926 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 8.36 MB 2026-04-25 03:32:38 · 1.1936 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:44:25 · 1.1936 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:33:34 · 1.1978 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:29:19 · 1.2034 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:27:05 · 1.2040 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:33:16 · 1.2092 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:53:15 · 1.2355 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:46:51 · 1.2367 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:30:33 · 1.2470 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:33:44 · 1.2537 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:34:33 · 1.2891 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:49:57 · 1.3718 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:34:23 · 1.3808 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:33:25 · 1.4565 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB 2026-04-25 03:31:48 · 1.6107 s · HIGH · Bottleneck Detected: Optimize Generator · VRAM as reported 24.36 MB
p50
1.0956 s
p95
1.2367 s
p99
1.4565 s
p50 to p99
33% jitter

Latency ladder

Llama 3.1 8B · dedicated NVIDIA VRAM · n = 1,000 · summary statistics

p50
2.3219 s
p95
2.4489 s
p99
2.5029 s
avg
2.3296 s
p50 to p99
7.8% jitter

Latency in seconds. Both axes cover the same range relative to their own median, so the bands compare directly.

FIG. 5 · Every dot is a real request

request · 2026-04-25 03:41:02 · total 1.2132 s

analyze_sentiment
0.1176 s
LOW · Healthy
generate_response
1.0956 s
HIGH · Bottleneck Detected: Optimize Generator

Generation is ~92% of request time and ~11x the sentiment stage. Flagged on 167 of 176 requests.

FIG. 6 · One request, two stages
L5 / SURFACE

Call ended · 0:17

Building something with AI? Let's talk.

Datasheet

Education
D. J. Sanghvi College of Engineering · B.E. Computer Engineering, Minor in Data Science · CGPA 9.11/10
Recognition
NPTEL Top 1% nationally, Python for Data Science
AI & Agents
LLM pipelines · prompt engineering · multi-agent systems · guardrails · OpenAI Agents SDK · CrewAI · RAG
Voice & Telephony
Retell AI · Twilio · Vobiz · ElevenLabs · HeyGen
Automation & GTM
Make · Zapier · LeadSquared CRM · webhooks · WhatsApp · outbound email · short-form video
Engineering
Python · JavaScript · SQL · FastAPI · Node.js · Next.js · PyTorch · Docker · Git · Claude Code daily
↑ Call again