containers/ramalama
The goal of RamaLama is to make working with AI boring.
Language:Shell
Total stars: 640
Stars trend:
#shell
#ai, #containers, #inferenceserver, #llamacpp, #llm, #podman, #vllm
The goal of RamaLama is to make working with AI boring.
Language:Shell
Total stars: 640
Stars trend:
31 Jan 2025
11am ▏ +1
12pm ███▌ +28
1pm ███ +24
2pm ███████ +56
3pm ████▋ +37
4pm ████▉ +39#shell
#ai, #containers, #inferenceserver, #llamacpp, #llm, #podman, #vllm
llmware-ai/llmware
Unified framework for building enterprise RAG pipelines with small, specialized models
Language:Python
Total stars: 8842
Stars trend:
#python
#agents, #generativeaitools, #llamacpp, #llm, #onnx, #openvino, #parsing, #retrievalaugmentedgeneration, #smallspecializedmodels
Unified framework for building enterprise RAG pipelines with small, specialized models
Language:Python
Total stars: 8842
Stars trend:
10 Feb 2025
12am ▏ +1
1am ▏ +1
2am +0
3am +0
4am ▏ +1
5am ████▊ +38
6am ██▎ +18
7am ██ +16
8am ▋ +5
9am ▊ +6
10am ████████████████▉ +135#python
#agents, #generativeaitools, #llamacpp, #llm, #onnx, #openvino, #parsing, #retrievalaugmentedgeneration, #smallspecializedmodels
Lizonghang/prima.cpp
prima.cpp: Speeding up 70B-scale LLM inference on low-resource everyday home clusters
Language:C++
Total stars: 101
Stars trend:
#cplusplus
#distributedai, #llamacpp, #llminference, #ondevicellms
prima.cpp: Speeding up 70B-scale LLM inference on low-resource everyday home clusters
Language:C++
Total stars: 101
Stars trend:
15 Apr 2025
2am ██ +16
3am ██▋ +21
4am █ +8
5am ▌ +4
6am █ +8
7am ▌ +4
8am ▍ +3
9am ▍ +3
10am ▏ +1
11am ▋ +5
12pm ▋ +5#cplusplus
#distributedai, #llamacpp, #llminference, #ondevicellms
dipampaul17/KVSplit
Run larger LLMs with longer contexts on Apple Silicon by using differentiated precision for KV cache quantization. KVSplit enables 8-bit keys & 4-bit values, reducing memory by 59% with <1% quality loss. Includes benchmarking, visualization, and one-command setup. Optimized for M1/M2/M3 Macs with Metal support.
Language:Python
Total stars: 144
Stars trend:
#python
#applesilicon, #generativeai, #kvcache, #llamacpp, #llm, #m1, #m2, #m3, #memoryoptimization, #metal, #optimization, #quantization
Run larger LLMs with longer contexts on Apple Silicon by using differentiated precision for KV cache quantization. KVSplit enables 8-bit keys & 4-bit values, reducing memory by 59% with <1% quality loss. Includes benchmarking, visualization, and one-command setup. Optimized for M1/M2/M3 Macs with Metal support.
Language:Python
Total stars: 144
Stars trend:
16 May 2025
7pm ▏ +1
8pm █████▌ +44
9pm ████▊ +38
10pm ███▋ +29
11pm ██▎ +18#python
#applesilicon, #generativeai, #kvcache, #llamacpp, #llm, #m1, #m2, #m3, #memoryoptimization, #metal, #optimization, #quantization
llmware-ai/llmware
Unified framework for building enterprise RAG pipelines with small, specialized models
Language:Python
Total stars: 13572
Stars trend:
#python
#agents, #generativeaitools, #llamacpp, #llm, #onnx, #openvino, #parsing, #retrievalaugmentedgeneration, #smallspecializedmodels
Unified framework for building enterprise RAG pipelines with small, specialized models
Language:Python
Total stars: 13572
Stars trend:
24 May 2025
8am ████ +32
9am █▍ +11
10am █▎ +10
11am █▍ +11
12pm █ +8
1pm ▊ +6
2pm █▏ +9
3pm █▌ +12
4pm ▌ +4
5pm ▎ +2
6pm ▍ +3
7pm ▎ +2#python
#agents, #generativeaitools, #llamacpp, #llm, #onnx, #openvino, #parsing, #retrievalaugmentedgeneration, #smallspecializedmodels
menloresearch/jan
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer
Language:TypeScript
Total stars: 29967
Stars trend:
#typescript
#electron, #gpt, #llama2, #llamacpp, #localai, #selfhosted
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer
Language:TypeScript
Total stars: 29967
Stars trend:
17 Jun 2025
2am ▏ +1
3am ▎ +2
4am +0
5am ▍ +3
6am ▏ +1
7am ▏ +1
8am ▎ +2
9am ▏ +1
10am █▏ +9
11am ██████▎ +50
12pm ██████▏ +49
1pm ███████▉ +63#typescript
#electron, #gpt, #llama2, #llamacpp, #localai, #selfhosted