Silence-GitHub/BBMetalImage
A high performance Swift library for GPU-accelerated image/video processing based on Metal.
Language: Swift
#filter #image #image_editor #image_processor #ios #jpeg #metal #png #swift
Stars: 186 Issues: 1 Forks: 14
https://github.com/Silence-GitHub/BBMetalImage
A high performance Swift library for GPU-accelerated image/video processing based on Metal.
Language: Swift
#filter #image #image_editor #image_processor #ios #jpeg #metal #png #swift
Stars: 186 Issues: 1 Forks: 14
https://github.com/Silence-GitHub/BBMetalImage
GitHub
GitHub - Silence-GitHub/BBMetalImage: A high performance Swift library for GPU-accelerated image/video processing based on Metal.
A high performance Swift library for GPU-accelerated image/video processing based on Metal. - Silence-GitHub/BBMetalImage
oct0xor/mgs2sos
This mod lets you play MGS2: Substance with the 3rd person camera (and game controls) from MGS3: Subsistence
Language: C++
#metal_gear_solid #metal_gear_solid_2 #mgs #mgs2
Stars: 117 Issues: 5 Forks: 5
https://github.com/oct0xor/mgs2sos
This mod lets you play MGS2: Substance with the 3rd person camera (and game controls) from MGS3: Subsistence
Language: C++
#metal_gear_solid #metal_gear_solid_2 #mgs #mgs2
Stars: 117 Issues: 5 Forks: 5
https://github.com/oct0xor/mgs2sos
GitHub
GitHub - oct0xor/mgs2sos: This mod lets you play MGS2: Substance with the 3rd person camera (and game controls) from MGS3: Subsistence
This mod lets you play MGS2: Substance with the 3rd person camera (and game controls) from MGS3: Subsistence - oct0xor/mgs2sos
👍2🔥1
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
#apple_silicon #generative_ai #kv_cache #llama_cpp #llm #m1 #m2 #m3 #memory_optimization #metal #optimization #quantization
Stars: 222 Issues: 1 Forks: 5
https://github.com/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
#apple_silicon #generative_ai #kv_cache #llama_cpp #llm #m1 #m2 #m3 #memory_optimization #metal #optimization #quantization
Stars: 222 Issues: 1 Forks: 5
https://github.com/dipampaul17/KVSplit
GitHub
GitHub - dipampaul17/KVSplit: Run larger LLMs with longer contexts on Apple Silicon by using differentiated precision for KV cache…
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 &am...