| | Inference at the edge: Efficient transformer model inference on-device (github.com/ggerganov) |
| 3 points by lioeters on July 2, 2023 | past |
|
| | WIP Llama.cpp Vulkan Implementations (github.com/ggerganov) |
| 24 points by brucethemoose2 on July 1, 2023 | past | 1 comment |
|
| | Falcon 40B Working on Ggml (github.com/ggerganov) |
| 5 points by __anon-2023__ on June 15, 2023 | past |
|
| | Llama.cpp: Full CUDA GPU Acceleration (github.com/ggerganov) |
| 728 points by gzer0 on June 13, 2023 | past | 310 comments |
|
| | K-Quants (github.com/ggerganov) |
| 3 points by tosh on June 10, 2023 | past |
|
| | Llama.cpp: Roadmap June 2023 (github.com/ggerganov) |
| 1 point by tosh on June 7, 2023 | past |
|
| | Full GPU Inference of LLaMA on Apple Silicon Using Metal (github.com/ggerganov) |
| 4 points by behnamoh on June 5, 2023 | past |
|
| | GGML: Replit and Mosaic MPT Support (github.com/ggerganov) |
| 1 point by tosh on May 12, 2023 | past |
|
| | Ggwave: Message people over sound (github.com/ggerganov) |
| 136 points by BasedDebianUsr on May 1, 2023 | past | 46 comments |
|
| | Whisper.cpp v1.4.0 (github.com/ggerganov) |
| 162 points by tosh on April 30, 2023 | past | 45 comments |
|
| | llama.cpp: Roadmap May 2023 (github.com/ggerganov) |
| 97 points by tosh on April 30, 2023 | past | 6 comments |
|
| | StableLM already being ported to ggml (github.com/ggerganov) |
| 3 points by theolivenbaum on April 20, 2023 | past |
|
| | Ggwave: Tiny Data-over-Sound Library (github.com/ggerganov) |
| 2 points by lachlan_gray on April 19, 2023 | past |
|
| | Talk.wasm: OpenAI's Whisper run in browser (github.com/ggerganov) |
| 2 points by behnamoh on April 18, 2023 | past |
|
| | Whisper.cpp now has CoreML suppprt (github.com/ggerganov) |
| 70 points by schappim on April 15, 2023 | past | 5 comments |
|
| | Llama.cpp: Add GPU support to ggml (github.com/ggerganov) |
| 3 points by mromanuk on April 12, 2023 | past |
|
| | [flagged] Revert for jart’s llama.cpp MMAP miracles (github.com/ggerganov) |
| 86 points by mmoustafa on April 2, 2023 | past | 86 comments |
|
| | [flagged] 30B model now needs only 5.8GB of RAM? How? (github.com/ggerganov) |
| 31 points by olalonde on April 1, 2023 | past | 11 comments |
|
| | Llama.cpp 30B runs with only 6GB of RAM now (github.com/ggerganov) |
| 1311 points by msoad on March 31, 2023 | past | 414 comments |
|
| | Keytap2 – acoustic keyboard eavesdropping based on language n-gram frequencies (github.com/ggerganov) |
| 2 points by tontonius on March 31, 2023 | past |
|
| | The Diff Challenge (github.com/ggerganov) |
| 29 points by another on March 22, 2023 | past | 3 comments |
|
| | Inference at the Edge (github.com/ggerganov) |
| 2 points by georgehill on March 17, 2023 | past |
|
| | Inference at the Edge (github.com/ggerganov) |
| 4 points by Mizza on March 16, 2023 | past |
|
| | Run a GPT-3 style AI on your local machine, fully on premise (github.com/ggerganov) |
| 2 points by luispa on March 14, 2023 | past |
|
| | LLaMA 7B model running on 4GB RAM Raspberry Pi 4 (github.com/ggerganov) |
| 6 points by amrrs on March 12, 2023 | past |
|
| | Llama.cpp: Port of Facebook's LLaMA model in C/C++, with Apple Silicon support (github.com/ggerganov) |
| 989 points by mrtksn on March 10, 2023 | past | 284 comments |
|
| | Talk = GPT-2 and Whisper and WASM (github.com/ggerganov) |
| 189 points by tomthe on Dec 7, 2022 | past | 50 comments |
|
| | Show HN: Port of OpenAI's Whisper model in C/C++ (github.com/ggerganov) |
| 399 points by ggerganov on Dec 6, 2022 | past | 87 comments |
|
| | Whisper: performant port of OpenAI's Whisper spech recognition model in C/C++ (github.com/ggerganov) |
| 4 points by nateb2022 on Nov 30, 2022 | past |
|
| | CPU Port of OpenAI's Whisper Speech to Text (github.com/ggerganov) |
| 41 points by abetusk on Nov 28, 2022 | past | 3 comments |
|
|
| More |
