doing something

Peak Energy just shipped the US's first grid-scale sodium-ion battery
Article, Comments

Peak Energy just shipped the US's first grid-scale sodium-ion battery

Peak Energy debuts the US's first grid-scale sodium-ion battery, cutting costs and boosting reliability with passive cooling tech.

124 views08:16

doing something

Alex

https://www.cerebras.ai/blog/introducing-cerebras-code

Other coding models:

- CodeGemma
- Codestral
- Code LLaMA (there variants: Python, instruct, base)

- StarCoder

- DeepSeek Coder

- Mellum (Python, Kotline, Base)

- GLM 4.5
- CodeGeeX

144 viewsedited 09:00

doing something

tg_image_3086276668.png

30.8 KB

#daily_pain

125 views10:16

doing something

https://github.com/EricLBuehler/mistral.rs

Wanna try it to do local inference with Gemma models

Build with:


MISTRALRS_METAL_PRECOMPILE=0 cargo build --release --features "metal accelerate"

#rust

135 viewsedited 11:27

doing something

https://github.com/EricLBuehler/mistral.rs Wanna try it to do local inference with Gemma models Build with: MISTRALRS_METAL_PRECOMPILE=0 cargo build --release --features "metal accelerate" #rust

It works

131 views11:48

doing something

https://github.com/EricLBuehler/mistral.rs Wanna try it to do local inference with Gemma models Build with: MISTRALRS_METAL_PRECOMPILE=0 cargo build --release --features "metal accelerate" #rust

It has Python bindings with useful things

https://github.com/EricLBuehler/mistral.rs/blob/master/examples/python/mcp_client.py

116 viewsedited 12:00

doing something

https://github.com/mostlygeek/llama-swap

#llm

GitHub

GitHub - mostlygeek/llama-swap: Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc - mostlygeek/llama-swap

117 views12:27

doing something

https://github.com/eleiton/ollama-intel-arc

#llm

GitHub

GitHub - eleiton/ollama-intel-arc: Make use of Intel Arc Series GPU to Run Ollama, StableDiffusion, Whisper and Open WebUI, for…

Make use of Intel Arc Series GPU to Run Ollama, StableDiffusion, Whisper and Open WebUI, for image generation, speech recognition and interaction with Large Language Models (LLM). - eleiton/ollama-...

127 views12:35

doing something

https://github.com/intel/ipex-llm

#llm

GitHub

GitHub - intel/ipex-llm: Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma…

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discr...

153 views12:39

doing something

Hugging Face has a page with available providers and model list they serve

https://huggingface.co/inference/models

It shows the speed in tokens/s so you can choose one for faster inference

142 viewsedited 13:21

doing something

Hugging Face has a page with available providers and model list they serve https://huggingface.co/inference/models It shows the speed in tokens/s so you can choose one for faster inference

I've chose LLaMA to check grammar mistakes in my codebase

Time is 1.5 seconds for everything

❤1

145 views13:22

doing something

https://github.com/bahdotsh/zp

What we had on Apple devices, now possible on Linux

#rust

GitHub

GitHub - bahdotsh/zp: A cli tool to copy things!

A cli tool to copy things! Contribute to bahdotsh/zp development by creating an account on GitHub.

162 views15:08