mlc-ai/web-llm

Issues

• Phi 3 Mini output near random (Phi-3-mini-4k-instruct-q4f16_1-MLC)

  #519 opened 2 months ago by cdrini
  10

• Engine Reuse Fails with Different JSON Schemas - "Module has already been disposed" Error

  #560 opened 4 days ago by SMarioMan
  3

• Error: Module has already been disposed

  #486 opened 4 days ago by talperetz
  5

• cannot read properties of undefined - description

  #572 opened 5 days ago by flatsiedatsie
  1

• New error: DXGI_ERROR_DEVICE_HUNG (0x887A0006)

  #489 opened 3 months ago by time2bot
  1

• Convert gpt 2 models

  #562 opened 11 days ago by ArpanDhot
  0

• Usage Stats in Intermediate Steps

  #559 opened 16 days ago by jdp8
  3

• Use subgroup operations when possible

  #553 opened a month ago by beaufortfrancois
  5

• Feature request: engine.preload()

  #529 opened 2 months ago by flatsiedatsie
  5

• Deploy small LLM in a chrome extension

  #510 opened 2 months ago by ArpanDhot
  2

• [Tracking][WebLLM] Function calling (beta) and Embeddings

  #526 opened 2 months ago by CharlieFRuan
  1

• support concurrent inference from multiple models

  #512 opened a month ago by mikestaub
  4

• Support concurrent requests to a single model instance

  #522 opened a month ago by LEXNY
  5

• DuckDB-NSQL-7B Model

  #554 opened a month ago by PureEngineering
  0

• Model request (Aya-23)

  #483 opened 3 months ago by time2bot
  1

• vercel/ai provider integration

  #551 opened a month ago by louis030195
  1

• TypeError: Cannot read properties of undefined (reading 'origin')

  #544 opened a month ago by alucarded
  1

• I can't find a method to stop a conversation in progress.

  #540 opened a month ago by kawayuta
  1

• Sending raw text to the model

  #507 opened 2 months ago by loristns
  4

• Are old models being removed?

  #487 opened 2 months ago by flatsiedatsie
  3

• Gemma 2 2B crashes on mobile phone

  #524 opened 2 months ago by flatsiedatsie
  16

• Request: Allow deletion of individual cached models.

  #516 opened 2 months ago by AndrewKeYanzhe
  3

• LLama 3.1 Error: Device was lost during reload. This can happen due to insufficient memory or other GPU constraints. Detailed error: [object GPUDeviceLostInfo]. Please try to reload WebLLM with a less resource-intensive model.

  #517 opened 2 months ago by djaffer
  4

• Runing LLM in a webworker fails due to loglevel dependency

  #511 opened 2 months ago by jauniusmentimeter
  1

• Custom model outputs garbage in firefox nightly, works fine in chrome.

  #518 opened 2 months ago by gulan28
  0

• How to let the user cancel loading the model and stop it from fetching params

  #499 opened 3 months ago by JohnReginaldShutler
  3

• anyone tried to run web-llm in tauri?

  #515 opened 2 months ago by louis030195
  0

• Deply llama 3 40 billion parameters model

  #506 opened 2 months ago by ArpanDhot
  4

• Example for using web worker with next js

  #496 opened 2 months ago by djaffer
  1

• Which LLM models can run on 6GB RTX 4050?

  #500 opened 2 months ago by radiantone
  2

• Can I initialize existing model with random weights?

  #505 opened 2 months ago by lostmsu
  0

• wasm optimization？

  #494 opened 3 months ago by 137591
  1

• TOO SLOW in downloading models from huggingface when running 'mlc_llm package'

  #504 opened 2 months ago by Foursheepsir
  0

• [Bug] Converted model outputs gibberish text

  #502 opened 2 months ago by gulan28
  1

• Error: Failed to execute 'mapAsync' on 'GPUBuffer'

  #497 opened 3 months ago by hanlily666
  0

• Microsoft just released a more capable new version over Phi 3 Mini

  #495 opened 3 months ago by flatsiedatsie
  0

• DOM manipulation (use case: filtering web search results locally)

  #465 opened 3 months ago by eMPee584
  2

• How to actually use WebLLM

  #493 opened 3 months ago by mirdulvultr
  3

• Inconsistent and unreliable outputs on mobile as opposed to on pc/laptop for -1k models

  #485 opened 3 months ago by JohnReginaldShutler
  1

• [Tracking] Improve error handling by having customized error types

  #470 opened 3 months ago by Neet-Nestor
  3

• model request: Llama-3-8B-Web

  #491 opened 3 months ago by talperetz
  0

• How to fine tuning the model in the browser?

  #488 opened 3 months ago by Bert0324
  0

• Abort `reload()` if receiving another `reload()` call

  #484 opened 3 months ago by Neet-Nestor
  0

• Model request: moondream (tiny vision model)

  #482 opened 3 months ago by darkvertex
  0

• Please ensure you have called `MLCEngine.reload(model)` to load the model before initiating chat operations

  #477 opened 3 months ago by radiantone
  3

• TypeError: Failed to execute 'add' on 'Cache': Request failed [RedPajama-INCITE-Chat-3B-v1-q4f32_1-MLC-1k]

  #474 opened 3 months ago by JohnReginaldShutler
  7

• Running the MLCengine completion in the service worker results in `Receiving end does not exist`

  #469 opened 3 months ago by talperetz
  10

• Allow specifying optional `onDisconnect` callback when creating ServiceWorkerMLCEngine

  #480 opened 3 months ago by t83714
  0

• Allow specifying optional `extensionId` when creating `ServiceWorkerMLCEngine`

  #479 opened 3 months ago by t83714
  0

• "Only one of context_window_size and sliding_window_size can be positive"

  #478 opened 3 months ago by flatsiedatsie
  1