mdrokz rust-llama.cpp issues

mdrokz / rust-llama.cpp

LLama.cpp rust bindings

https://crates.io/crates/llama_cpp_rs/

MIT License

287 stars 42 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

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

#43 BenjaminMassey closed 1 week ago
0
fix build.rs to build under macOS

#42 gmerlino closed 1 week ago
2
Fix CUDA on Windows

#41 glcraft closed 2 months ago
2
Compiling with metal feature has `ggml-metal.o` linker failure

#40 tc-wolf opened 4 months ago
3
Fix compilation w/ metal feature enabled

#39 tc-wolf opened 4 months ago
7
Bug cannot build correct in macos with m2 chip

#38 bruceunx opened 4 months ago
0
Maintance and improvements

#37 philschmid opened 4 months ago
6
Update-llamacpp

#36 casualjim closed 4 months ago
0
fix missized vec

#35 kallsyms closed 5 months ago
1
chore(deps): bump shlex from 1.1.0 to 1.3.0

#34 dependabot[bot] opened 5 months ago
0
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

#33 pixelspark closed 5 months ago
0
Include ggml-metal.metal file in source code

#32 pixelspark closed 5 months ago
1
Support for GBNF Grammars

#31 benbot opened 6 months ago
2
Using metal and `n_gpu_layers` produces no tokens

#30 jasonw247 opened 6 months ago
5
Error running Phi2 Models

#29 jasonw247 opened 6 months ago
0
remove or add a way to disable `println!("count {}", reverse_count);`

#28 alescdb opened 6 months ago
1
upgrade llama.cpp to b1742

#27 bedwards closed 6 months ago
0
clang - fatal error: 'assert.h' file not found

#26 RussellCanfield opened 6 months ago
2
upgraded llama.cpp to b1575

#25 janeisklar closed 7 months ago
0
Error when enabling CUDA on Windows

#24 Kuinox closed 2 months ago
12
`LLama` is not `Send`

#23 tadad closed 7 months ago
4
Sometimes crashes with UTF8 error

#22 kimtore opened 7 months ago
3
Multithreading support

#21 markcda closed 7 months ago
0
Fixed gpt_params::~gpt_params double memory deallocation

#20 markcda closed 8 months ago
0
Slow Performance compared to Python Binding

#19 JewishLewish closed 8 months ago
1
Feature flag metal: Fails to load model when n_gpu_layers > 0

#18 phudtran opened 8 months ago
8
llama.cpp ./embedding

#17 Philipp-Sc opened 8 months ago
4
Error in loading models

#16 RodrigoSdeCarvalho closed 8 months ago
5
Cant build on Ubuntu 22.04

#15 RodrigoSdeCarvalho closed 8 months ago
1
Add explicit C and C++ versions to compile calls

#14 jmickeyd closed 8 months ago
0
Update to latest llama.cpp to allow usage of LLaMAv2 and GGUF models

#13 kouta-kun closed 8 months ago
0
Fix windows build

#12 mdrokz closed 9 months ago
0
Cant build on Mac aarch64

#11 Scaletta closed 8 months ago
0
Cant compile on Win64

#10 Scaletta closed 9 months ago
2
Metal support for macos

#9 mdrokz closed 9 months ago
0
fix bad examples link

#8 dmitris closed 9 months ago
0
Implement blas support

#7 mdrokz closed 10 months ago
0
fix: change to proper commit

#6 mdrokz closed 10 months ago
0
Not cloning llama.cpp submodule

#5 PainSled closed 10 months ago
2
Promote to master

#4 mdrokz closed 12 months ago
0
Transform project as library for publishing to crates.io

#3 mdrokz closed 12 months ago
0
Implement build system for building llama.cpp

#2 mdrokz closed 1 year ago
0
Implement options mod

#1 mdrokz closed 1 year ago
0