Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / Atome-FE/llama-node issues and pull requests

#124 - What files are compatible?

Issue - State: open - Opened by bedcoding 8 months ago

#123 - Alternative?

Issue - State: open - Opened by linonetwo 11 months ago

#122 - GGUF support?

Issue - State: open - Opened by Tokoyami about 1 year ago

#121 - cannot use RWKV models

Issue - State: open - Opened by rozek about 1 year ago - 16 comments

#120 - Instructions for use with Electron

Issue - State: open - Opened by bishwenduk029 about 1 year ago

#119 - Time printings are gone

Issue - State: open - Opened by CodeJjang about 1 year ago

#118 - napi: not found on debian bullseye

Issue - State: open - Opened by loretoparisi about 1 year ago - 5 comments

#116 - Can't run example on llama-2-13b-chat q4_0

Issue - State: open - Opened by gioragutt over 1 year ago - 2 comments

#115 - Support for passing grammars

Issue - State: open - Opened by arthurwolf over 1 year ago

#114 - GPU version build not using GPU

Issue - State: open - Opened by deonis1 over 1 year ago - 11 comments

#113 - Segmentation fault

Issue - State: open - Opened by ZGltYQ over 1 year ago - 1 comment

#112 - chore(deps-dev): bump vite from 4.3.1 to 4.3.9

Pull Request - State: open - Opened by dependabot[bot] over 1 year ago
Labels: dependencies

#111 - chore(deps-dev): bump semver from 7.5.0 to 7.5.2

Pull Request - State: open - Opened by dependabot[bot] over 1 year ago
Labels: dependencies

#109 - fatal runtime error: Rust cannot catch foreign exceptions

Issue - State: open - Opened by HolmesDomain over 1 year ago - 5 comments

#108 - Llama2 quantized q5_1

Issue - State: open - Opened by HolmesDomain over 1 year ago - 1 comment

#107 - Discord Access

Issue - State: closed - Opened by HolmesDomain over 1 year ago - 1 comment

#106 - Upgrade llama-cpp to master-294f424

Pull Request - State: closed - Opened by fardjad over 1 year ago - 1 comment

#105 - Use custom tokenizer

Issue - State: open - Opened by linonetwo over 1 year ago

#104 - 中文乱码

Issue - State: open - Opened by linonetwo over 1 year ago

#102 - Should bring details in error message

Issue - State: open - Opened by linonetwo over 1 year ago

#101 - Unsupported file version 101 when loading rwkv

Issue - State: open - Opened by linonetwo over 1 year ago

#99 - Issue to build GPU version

Issue - State: closed - Opened by deonis1 over 1 year ago - 1 comment

#98 - Resolved #91, fixed LoadModel typo

Pull Request - State: closed - Opened by tommoffat over 1 year ago

#95 - Support for the new k-quant methods in Llama.cpp

Issue - State: open - Opened by synw over 1 year ago

#94 - the software has no reaction with no errors

Issue - State: open - Opened by adambnn over 1 year ago

#93 - use with Next.js (webpack fails to load binary file)

Issue - State: open - Opened by eagor over 1 year ago - 3 comments

#92 - Can't run the example on MacOS M1 pro

Issue - State: open - Opened by greenido over 1 year ago

#91 - Llama.cpp Typescript: Cannot find name 'LoadModel'

Issue - State: closed - Opened by synw over 1 year ago
Labels: bug

#88 - chore: sync recent rwkv.cpp version

Pull Request - State: closed - Opened by yorkzero831 over 1 year ago - 7 comments

#87 - update: refractor onnx

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#86 - update: upgrade llm to 0.2.0-dev

Pull Request - State: closed - Opened by fardjad over 1 year ago - 2 comments

#84 - Ggml v3 support in Llama.cpp

Issue - State: closed - Opened by synw over 1 year ago - 4 comments
Labels: sync deps

#83 - no kernel image is available for execution on the device

Issue - State: open - Opened by determo13 over 1 year ago - 2 comments

#81 - Error: Too many tokens predicted

Issue - State: closed - Opened by dhd5076 over 1 year ago - 1 comment

#80 - Error: Missing field `nGpuLayers`

Issue - State: open - Opened by bakiwebdev over 1 year ago - 6 comments
Labels: documentation, question

#79 - Failed to convert napi value into rust type `bool`

Issue - State: closed - Opened by determo13 over 1 year ago - 1 comment

#78 - Segmentation fault local cuda build

Issue - State: open - Opened by chrgeor over 1 year ago

#77 - Embeddings.js file does not work correctly

Issue - State: open - Opened by skirodev over 1 year ago

#76 - foreign exception error

Issue - State: open - Opened by ralyodio over 1 year ago - 12 comments
Labels: bug, ffi bug

#74 - app crashes when input is too long

Issue - State: closed - Opened by ralyodio over 1 year ago - 6 comments
Labels: bug

#73 - [ERROR] cublas `TypeError: this.instance.inference is not a function`

Issue - State: open - Opened by tchereau over 1 year ago - 3 comments

#72 - Illegal instruction (core dumped)

Issue - State: open - Opened by itz-coffee over 1 year ago - 4 comments

#71 - getting error after second run

Issue - State: closed - Opened by ralyodio over 1 year ago
Labels: bug

#70 - TypeError: llm._modelType is not a function

Issue - State: open - Opened by gaurav-cointab over 1 year ago - 1 comment
Labels: invalid

#69 - Code only using 4 CPU, when I have 16 CPU

Issue - State: open - Opened by gaurav-cointab over 1 year ago - 3 comments
Labels: enhancement

#68 - req: support async/await

Issue - State: open - Opened by ralyodio over 1 year ago - 8 comments
Labels: question, wontfix

#67 - Error: Failed to convert napi value Function into rust type `f64`

Issue - State: open - Opened by ralyodio over 1 year ago - 5 comments
Labels: question, wontfix

#66 - feat: update cuda dynamic compiling

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#64 - is this supposed to have a gpu to run?

Issue - State: closed - Opened by ralyodio over 1 year ago - 2 comments

#63 - feat: implement chat feature to rwkv

Pull Request - State: closed - Opened by yorkzero831 over 1 year ago - 2 comments

#62 - feat: upgrade llama-rs to llm

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#61 - update: sync latest llama.cpp branch

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#58 - feat: impl abortable inference

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#57 - [Error: Could not load model] { code: 'GenericFailure' }

Issue - State: open - Opened by ralyodio over 1 year ago - 8 comments

#56 - langchain integration

Issue - State: open - Opened by luca-saggese over 1 year ago - 2 comments
Labels: enhancement

#55 - basic unified API for all backends

Issue - State: open - Opened by end-me-please over 1 year ago - 3 comments
Labels: enhancement

#54 - ¿Update cross-compile.mts with aarch64 architecture?

Issue - State: open - Opened by yupihello over 1 year ago - 1 comment

#53 - How to train the model with this library?

Issue - State: closed - Opened by dev-bre over 1 year ago - 1 comment
Labels: wontfix

#51 - feature: impl naive gpt2

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#50 - How to use the GPU?

Issue - State: closed - Opened by dev-bre over 1 year ago - 16 comments
Labels: enhancement

#49 - fix: utf8 encode issue

Pull Request - State: closed - Opened by yorkzero831 over 1 year ago - 2 comments

#48 - fix: rwkv cpp windows failing

Pull Request - State: closed - Opened by hlhr202 over 1 year ago - 7 comments

#47 - Interactive

Issue - State: open - Opened by luca-saggese over 1 year ago - 11 comments
Labels: question

#46 - fix: fix the problem of rwkv failing

Pull Request - State: closed - Opened by yorkzero831 over 1 year ago

#44 - @llama-node/rwkv-cpp only contains rwkv-cpp.darwin-arm64.node

Issue - State: closed - Opened by yorkzero831 over 1 year ago - 13 comments
Labels: bug

#43 - Version 0.0.34 gives drastic different ouput when paired with vicuna.

Issue - State: open - Opened by JoshuaeKaiser over 1 year ago - 3 comments
Labels: question

#42 - feat: temp workaround for cublas build

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#41 - How do I force the end of text generation?

Issue - State: open - Opened by MrFartFox over 1 year ago - 16 comments
Labels: question

#40 - Typo fix

Pull Request - State: closed - Opened by Dinex-dev over 1 year ago - 1 comment

#39 - feat: new inference resolve/reject type

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#38 - feature: llama cpp new sampling

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#36 - implement new sampling logic for llama.cpp

Issue - State: closed - Opened by hlhr202 over 1 year ago
Labels: enhancement

#35 - feat: impl cache session and load session

Pull Request - State: closed - Opened by hlhr202 over 1 year ago - 1 comment

#34 - [ASK] enable cuda with manual compilation

Issue - State: open - Opened by tchereau over 1 year ago - 10 comments
Labels: good first issue

#33 - feat: impl session snapshot, add comments for llama-rs params

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#32 - Failed to load modal

Issue - State: closed - Opened by Bazhan4ik over 1 year ago - 5 comments

#31 - feature: rwkv cpp backend

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#30 - Get started guideline for contributors

Issue - State: closed - Opened by hlhr202 over 1 year ago - 1 comment
Labels: documentation

#29 - chore: add more docs

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#28 - feature: move docs into codebase

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#27 - feat: upgrade to newest llama-rs so that we can support ggjt model

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#26 - Expand on install/usage instructions

Issue - State: closed - Opened by bakman2 over 1 year ago - 2 comments
Labels: documentation

#25 - fix: ci cross compile failure report

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#24 - Support for Prompt Caching/Restoring from llama-rs?

Issue - State: closed - Opened by end-me-please over 1 year ago - 14 comments
Labels: enhancement

#23 - llama-node does not display prompt in Deno environment

Issue - State: closed - Opened by KiraCoding over 1 year ago - 2 comments
Labels: wontfix

#22 - "libstdc++.so.6: version `GLIBCXX_3.4.29' not found" error with docker

Issue - State: closed - Opened by MegaR over 1 year ago - 5 comments
Labels: help wanted

#21 - dyld[50013]: missing symbol called

Issue - State: closed - Opened by Hoozia over 1 year ago - 11 comments

#20 - feat: maintain llama.cpp bindings locally.

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#19 - feat: add linux-musl build

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#18 - zsh: illegal hardware instruction

Issue - State: closed - Opened by loretoparisi over 1 year ago - 6 comments
Labels: bug

#16 - refractor: refine types

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#15 - chore: update llama-cpp readme

Pull Request - State: closed - Opened by hlhr202 over 1 year ago

#14 - Feature/llama cpp embedding and tokenization support

Pull Request - State: closed - Opened by hlhr202 over 1 year ago