mdrokz/rust-llama.cpp issues and pull requests

#45 - bump not applicable

Issue - State: closed - Opened by GIOVANNI-75 about 2 months ago

#44 - `ggml.o` missing.

Issue - State: open - Opened by vnermolaev 3 months ago - 2 comments

#43 - Removed count println from predict(..) as per #28

Pull Request - State: closed - Opened by BenjaminMassey 5 months ago

#42 - fix build.rs to build under macOS

Pull Request - State: closed - Opened by gmerlino 6 months ago - 2 comments

#41 - Fix CUDA on Windows

Pull Request - State: closed - Opened by glcraft 7 months ago - 2 comments

#40 - Compiling with metal feature has `ggml-metal.o` linker failure

Issue - State: open - Opened by tc-wolf 8 months ago - 3 comments

#39 - Fix compilation w/ metal feature enabled

Pull Request - State: open - Opened by tc-wolf 8 months ago - 7 comments

#38 - Bug cannot build correct in macos with m2 chip

Issue - State: open - Opened by bruceunx 9 months ago

#37 - Maintance and improvements

Issue - State: open - Opened by philschmid 9 months ago - 6 comments

#36 - Update-llamacpp

Pull Request - State: closed - Opened by casualjim 9 months ago

#35 - fix missized vec

Pull Request - State: closed - Opened by kallsyms 10 months ago - 1 comment
Labels: bugfix

#34 - chore(deps): bump shlex from 1.1.0 to 1.3.0

Pull Request - State: open - Opened by dependabot[bot] 10 months ago
Labels: dependencies

#33 - feat: patch the metal shader source code into the llama.cpp code at build time, so it is not needed to include the file in the cwd of the binary

Pull Request - State: closed - Opened by pixelspark 10 months ago
Labels: enhancement, bugfix

#32 - Include ggml-metal.metal file in source code

Issue - State: closed - Opened by pixelspark 10 months ago - 1 comment
Labels: enhancement

#31 - Support for GBNF Grammars

Issue - State: open - Opened by benbot 10 months ago - 2 comments

#30 - Using metal and `n_gpu_layers` produces no tokens

Issue - State: open - Opened by jasonw247 10 months ago - 5 comments

#29 - Error running Phi2 Models

Issue - State: open - Opened by jasonw247 10 months ago

#28 - remove or add a way to disable `println!("count {}", reverse_count);`

Issue - State: open - Opened by alescdb 10 months ago - 1 comment
Labels: bug

#27 - upgrade llama.cpp to b1742

Pull Request - State: closed - Opened by bedwards 11 months ago
Labels: enhancement

#26 - clang - fatal error: 'assert.h' file not found

Issue - State: open - Opened by RussellCanfield 11 months ago - 2 comments

#25 - upgraded llama.cpp to b1575

Pull Request - State: closed - Opened by janeisklar 12 months ago
Labels: enhancement

#24 - Error when enabling CUDA on Windows

Issue - State: closed - Opened by Kuinox 12 months ago - 12 comments
Labels: bug

#23 - `LLama` is not `Send`

Issue - State: closed - Opened by tadad about 1 year ago - 4 comments

#22 - Sometimes crashes with UTF8 error

Issue - State: open - Opened by kimtore about 1 year ago - 3 comments

#21 - Multithreading support

Pull Request - State: closed - Opened by markcda about 1 year ago
Labels: enhancement

#20 - Fixed gpt_params::~gpt_params double memory deallocation

Pull Request - State: closed - Opened by markcda about 1 year ago

#19 - Slow Performance compared to Python Binding

Issue - State: closed - Opened by JewishLewish about 1 year ago - 1 comment

#18 - Feature flag metal: Fails to load model when n_gpu_layers > 0

Issue - State: open - Opened by phudtran about 1 year ago - 8 comments
Labels: bug

#17 - llama.cpp ./embedding

Issue - State: open - Opened by Philipp-Sc about 1 year ago - 4 comments
Labels: question

#16 - Error in loading models

Issue - State: closed - Opened by RodrigoSdeCarvalho about 1 year ago - 5 comments
Labels: bug

#15 - Cant build on Ubuntu 22.04

Issue - State: closed - Opened by RodrigoSdeCarvalho about 1 year ago - 1 comment

#14 - Add explicit C and C++ versions to compile calls

Pull Request - State: closed - Opened by jmickeyd about 1 year ago
Labels: bugfix

#13 - Update to latest llama.cpp to allow usage of LLaMAv2 and GGUF models

Pull Request - State: closed - Opened by kouta-kun about 1 year ago
Labels: enhancement

#12 - Fix windows build

Pull Request - State: closed - Opened by mdrokz about 1 year ago - 1 comment
Labels: enhancement

#11 - Cant build on Mac aarch64

Issue - State: closed - Opened by Scaletta about 1 year ago
Labels: bug

#10 - Cant compile on Win64

Issue - State: closed - Opened by Scaletta about 1 year ago - 2 comments
Labels: bug

#9 - Metal support for macos

Pull Request - State: closed - Opened by mdrokz about 1 year ago
Labels: enhancement

#8 - fix bad examples link

Pull Request - State: closed - Opened by dmitris about 1 year ago
Labels: documentation

#7 - Implement blas support

Pull Request - State: closed - Opened by mdrokz about 1 year ago
Labels: enhancement

#6 - fix: change to proper commit

Pull Request - State: closed - Opened by mdrokz about 1 year ago
Labels: bugfix

#5 - Not cloning llama.cpp submodule

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

#4 - Promote to master

Pull Request - State: closed - Opened by mdrokz over 1 year ago
Labels: documentation, enhancement

#3 - Transform project as library for publishing to crates.io

Pull Request - State: closed - Opened by mdrokz over 1 year ago
Labels: documentation, enhancement

#2 - Implement build system for building llama.cpp

Pull Request - State: closed - Opened by mdrokz over 1 year ago
Labels: enhancement

#1 - Implement options mod

Pull Request - State: closed - Opened by mdrokz over 1 year ago
Labels: enhancement

GitHub / mdrokz/rust-llama.cpp issues and pull requests