Ecosyste.ms: Issues

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

GitHub / rustformers/llm issues and pull requests

#329 - feat: automatically run checks before commit

Pull Request - State: closed - Opened by philpax over 1 year ago
Labels: meta:maintenance

#328 - fix(metal): patch ggml-metal.m with shader code

Pull Request - State: closed - Opened by philpax over 1 year ago - 3 comments
Labels: topic:backend-support, os:macos

#325 - CUDA/OpenCL Acceleration

Pull Request - State: closed - Opened by LLukas22 over 1 year ago - 30 comments
Labels: topic:backend-support

#322 - Fix GPT-2 Positional Embeddings

Pull Request - State: closed - Opened by LLukas22 over 1 year ago

#320 - WeightedIndex error: invalid weight

Issue - State: open - Opened by andri-jpg over 1 year ago - 6 comments
Labels: issue:bug, model:gpt-neox, arch:arm64

#319 - Write basic automated tests that can be run locally

Issue - State: closed - Opened by philpax over 1 year ago - 1 comment
Labels: issue:enhancement, meta:maintenance

#318 - Modular sampler

Issue - State: closed - Opened by philpax over 1 year ago - 3 comments
Labels: issue:enhancement, topic:api-design

#316 - Attempt to guess the architecture of the model if not specified

Issue - State: closed - Opened by philpax over 1 year ago - 2 comments
Labels: issue:enhancement, app:cli

#315 - CUDA decoding

Issue - State: closed - Opened by jafioti over 1 year ago - 16 comments
Labels: issue:enhancement, topic:backend-support

#313 - Add Falcon Support

Pull Request - State: closed - Opened by LLukas22 over 1 year ago
Labels: topic:model-support

#304 - Is HuggingFaceH4/starchat-beta supported?

Issue - State: open - Opened by laurids-reichardt over 1 year ago - 4 comments
Labels: topic:model-support

#296 - Default to f16 model memory k/v in llm CLI and InferenceSessionConfig

Pull Request - State: closed - Opened by KerfuffleV2 over 1 year ago - 3 comments

#293 - Support Falcon

Issue - State: open - Opened by zcourts over 1 year ago - 10 comments
Labels: topic:model-support

#286 - Does it support the new GGMLv3 quantization methods?

Issue - State: open - Opened by Exotik850 over 1 year ago - 5 comments

#286 - Does it support the new GGMLv3 quantization methods?

Issue - State: open - Opened by Exotik850 over 1 year ago - 4 comments

#286 - Does it support the new GGMLv3 quantization methods?

Issue - State: open - Opened by Exotik850 over 1 year ago - 4 comments

#284 - Automatically check that model hyperparameters can roundtrip through GGML read/write

Issue - State: closed - Opened by philpax over 1 year ago
Labels: meta:maintenance

#274 - Context clone may not actually preserve the memory

Issue - State: open - Opened by philpax over 1 year ago - 2 comments
Labels: issue:bug, topic:api-design

#272 - refactor: remove model-associated inference params

Pull Request - State: open - Opened by philpax over 1 year ago

#271 - Add HuggingFace's Tokenizer

Pull Request - State: open - Opened by RedBoxing over 1 year ago

#270 - Pull upstream changes into GptNeox

Pull Request - State: open - Opened by LLukas22 over 1 year ago - 3 comments

#269 - llm-llama's old version of rust-tokenizers and protobuf conflicts with rust-bert

Issue - State: closed - Opened by dimfeld over 1 year ago - 3 comments
Labels: bug, maintenance, llama

#267 - Lower level API?

Issue - State: open - Opened by spion over 1 year ago - 1 comment
Labels: enhancement

#266 - Update to latest upstream GPT-2 implementation

Issue - State: open - Opened by philpax over 1 year ago
Labels: enhancement, model-support

#265 - Update to latest upstream GPT-J implementation

Issue - State: open - Opened by philpax over 1 year ago
Labels: enhancement, model-support

#263 - feat: cloning trait (DRAFT)

Pull Request - State: closed - Opened by louisgv over 1 year ago - 1 comment
Labels: topic:api-design

#262 - Remove LLaMA "old_loader"

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

#260 - Context size consistency & fixes

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

#259 - Update headings

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

#258 - More CONTRIBUTING updates

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

#257 - Perplexity can/will segfault over large input sizes

Issue - State: open - Opened by philpax over 1 year ago - 3 comments
Labels: issue:bug, app:cli

#256 - More model standardization

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

#255 - Model architectures should appear in alphabetic order

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

#254 - Lingering NeoX reference

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

#253 - README updates for v0.2

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

#252 - Support GGJT v3

Issue - State: open - Opened by philpax over 1 year ago - 1 comment
Labels: enhancement, breaking change

#251 - Fix perplexity calculation

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

#250 - publish llm-mpt crate

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

#249 - Model verification

Issue - State: open - Opened by mhykes over 1 year ago - 3 comments
Labels: enhancement, maintenance

#248 - Add perplexity calculation and cli-arg

Pull Request - State: closed - Opened by tanmaysachan over 1 year ago - 3 comments

#247 - Typo fix in extern function name

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

#246 - Update to latest upstream GPT-NeoX implementation / Fix GPT-NeoX inference

Issue - State: open - Opened by philpax over 1 year ago - 1 comment
Labels: bug, model-support

#245 - feat: support quantizing with a GGML container

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

#244 - Write a 0.2 changelog

Issue - State: open - Opened by philpax over 1 year ago - 8 comments
Labels: issue:documentation

#243 - RWKV support

Pull Request - State: open - Opened by RedBoxing over 1 year ago - 1 comment

#242 - fix: qnt0 build

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

#241 - Question: how to I get a InferenceSnapshot in session.infer callback

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

#240 - Ability to clone a Model

Issue - State: open - Opened by louisgv over 1 year ago - 1 comment
Labels: issue:enhancement, topic:api-design

#237 - Update Gpt-NeoX implementation

Pull Request - State: closed - Opened by LLukas22 over 1 year ago - 3 comments

#236 - fix: cancel the loading spinner in error cases

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

#235 - Constrained generation support

Issue - State: open - Opened by philpax over 1 year ago - 6 comments
Labels: issue:enhancement, topic:api-design

#234 - Build Errors

Issue - State: closed - Opened by mhykes over 1 year ago - 3 comments
Labels: bug

#233 - NeoX -> GPT-NeoX

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

#232 - Added support for multiple LoRA adapters

Pull Request - State: closed - Opened by LLukas22 over 1 year ago - 7 comments

#231 - Hot-swappable LoRa layers

Issue - State: open - Opened by daniel-vainsencher over 1 year ago
Labels: enhancement

#230 - How to run these models?

Issue - State: closed - Opened by realcarlos over 1 year ago - 10 comments
Labels: bug

#229 - Support for ChatGLM

Issue - State: open - Opened by xtuyaowu over 1 year ago - 3 comments
Labels: topic:model-support

#228 - Update to latest upstream BLOOM implementation / BLOOM Quantization does not work

Issue - State: open - Opened by danforbes over 1 year ago - 1 comment
Labels: bug, bloom

#227 - Support multiple LoRA adapters

Issue - State: closed - Opened by LLukas22 over 1 year ago - 6 comments
Labels: enhancement

#226 - Update GGML dependency

Pull Request - State: closed - Opened by danforbes over 1 year ago - 3 comments

#225 - Dynamically calculate the LoRA patching context size

Pull Request - State: closed - Opened by LLukas22 over 1 year ago - 1 comment

#224 - GGML README

Pull Request - State: closed - Opened by danforbes over 1 year ago - 6 comments

#223 - error failed to run custom build command for `ggml-sys v0.1.1 on Macos

Issue - State: closed - Opened by realcarlos over 1 year ago - 2 comments
Labels: bug

#222 - Support for `GPTBigCode`

Issue - State: closed - Opened by ekolawole over 1 year ago - 2 comments
Labels: topic:model-support

#221 - Refactor public API into modules

Issue - State: open - Opened by philpax over 1 year ago - 3 comments
Labels: issue:enhancement, meta:maintenance, meta:breaking-change

#220 - Start writing up developer documentation

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

#219 - Document optimization levels for users

Issue - State: closed - Opened by philpax over 1 year ago
Labels: documentation, enhancement

#218 - Implement MPT Model

Pull Request - State: closed - Opened by danforbes over 1 year ago - 4 comments
Labels: model-support

#217 - MPT model support

Pull Request - State: closed - Opened by LLukas22 over 1 year ago - 4 comments

#216 - Split up initial and per-message prompts for chat mode

Issue - State: closed - Opened by philpax over 1 year ago - 2 comments
Labels: issue:enhancement, app:cli

#215 - Update upstream GGML dependency

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

#214 - Support MPT

Issue - State: closed - Opened by philpax over 1 year ago - 2 comments
Labels: enhancement, model-support

#213 - Use mlc-llm as backend

Issue - State: open - Opened by shiqimei over 1 year ago - 1 comment
Labels: enhancement

#212 - GPT-J Will Not Accept Certain Tokens in Prompt

Issue - State: open - Opened by danforbes over 1 year ago - 5 comments
Labels: bug

#211 - Implement LoRA patching via the Loader

Pull Request - State: closed - Opened by LLukas22 over 1 year ago - 6 comments

#210 - Update to latest upstream LLaMA implementation

Issue - State: open - Opened by philpax over 1 year ago - 1 comment
Labels: enhancement, model-support, llama

#209 - Support new quantization formats for quantizer

Issue - State: open - Opened by philpax over 1 year ago
Labels: enhancement

#208 - Rename `NeoX` to `GptNeoX` across the board

Issue - State: closed - Opened by philpax over 1 year ago
Labels: enhancement, good first issue

#207 - [WIP] RWKV support

Pull Request - State: closed - Opened by philpax over 1 year ago - 2 comments
Labels: model-support

#206 - Fine-grain inference feedback

Pull Request - State: closed - Opened by danforbes over 1 year ago - 3 comments

#205 - How can I stop the inference to include the prompt tokens?

Issue - State: closed - Opened by juliooa over 1 year ago - 9 comments

#204 - Implement RedPajama as a NeoX Specialization

Pull Request - State: closed - Opened by danforbes over 1 year ago - 3 comments

#201 - how should i build a web interface?

Issue - State: closed - Opened by ralyodio over 1 year ago - 4 comments

#200 - Refactors from llm-chain integration

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

#199 - refactor: move load to KnownModel trait

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

#198 - Support the bit-shuffling changes from `llama.cpp`

Issue - State: closed - Opened by philpax over 1 year ago - 3 comments
Labels: enhancement

#197 - Set up `cargo release` to only emit one tag

Issue - State: closed - Opened by philpax over 1 year ago
Labels: issue:enhancement, meta:maintenance

#196 - Support for LoRA adapters?

Issue - State: closed - Opened by NatanFreeman over 1 year ago - 16 comments

#195 - Rework the inference API

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

#194 - Align CLI args w/ model string representations

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

#193 - Can this library be compiled to run on WebAssembly and within a Wasm container?

Issue - State: open - Opened by yelcat over 1 year ago - 3 comments
Labels: topic:backend-support

#192 - Add readme table that details which models can be used with which command

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

#191 - Replace custom ModelArchitecture impl with idiomatic traits

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

#190 - Support for GGML BLAS

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

#189 - Official support for Wizard?

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

#188 - fix #187 - skip over the BOS token for BLOOM

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

#187 - Skip over the BOS token where possible

Issue - State: closed - Opened by philpax over 1 year ago - 2 comments
Labels: bug, enhancement, bloom

#186 - Codegen Implementation

Pull Request - State: closed - Opened by hhamud over 1 year ago - 3 comments
Labels: help wanted, model-support

#185 - Bloom Inference

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