Comments (2)
This was fixed here: 7d9ed7b
Just pull, run make and it should be good
from llama.cpp.
Nice, that worked 🥳
main: mem per token = 71159620 bytes
main: load time = 15499.67 ms
main: sample time = 277.16 ms
main: predict time = 39353.45 ms / 285.17 ms per token
main: total time = 56266.87 ms
from llama.cpp.
Related Issues (20)
- llama : store token ids in the KV Cache
- Bug: Converted HF LoRA adapter on Llama 3.1 not loading. HOT 4
- Feature Request: Add support for Phi-3.5 MoE and Vision Instruct HOT 4
- obtain attention matrices during inference, similar to the output_attentions=True parameter in the transformers package
- Bug: phi 3.5 mini produces garbage past 4096 context HOT 3
- Bug: Missing "." in prompt template for Qwen2 HOT 3
- Feature Request: Simplified conversation mode interface
- Bug: Difficulties Using LLaMa.cpp Server and --prompt-cache [FNAME] (not supported?) HOT 6
- support Phi-3.5-MoE HOT 1
- Bug: Wiki link to hugging face example template redirects to a restricted page
- Bug: Compilation failure with CUDA support on Windows: No CUDA toolset found. HOT 1
- Bug: Processor features are determined at compile time HOT 4
- Refactor: Server reporting the correct model
- Bug: igpu HOT 3
- Refactor: Where is convert.py HOT 2
- Bug: GGML_ASSERT((qs.n_attention_wv == n_attn_layer) && "n_attention_wv is unexpected") failed with deepseek2 HOT 2
- Bug: Mac build failed using make
- Feature Request: Loading page for "/" and ".html" requests instead of json error.
- Feature Request: Add server support for chatglm3 HOT 1
- Bug: mixtral 8x7b instruct imatrix creation and quantization to IQ3_XXS broken: llama_model_quantize_internal: did not find weights for
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from llama.cpp.