liang.he 0599351262 wasi-nn: Add a new target for llama.cpp as a wasi-nn backend (#3709) ... Minimum support: - [x] accept (WasmEdge) customized model parameters. metadata. - [x] Target [wasmedge-ggml examples](https://github.com/second-state/WasmEdge-WASINN-examples/tree/master/wasmedge-ggml) - [x] basic - [x] chatml - [x] gemma - [x] llama - [x] qwen --- In the future, to support if required: - [ ] Target [wasmedge-ggml examples](https://github.com/second-state/WasmEdge-WASINN-examples/tree/master/wasmedge-ggml) - [ ] command-r. (>70G memory requirement) - [ ] embedding. (embedding mode) - [ ] grammar. (use the grammar option to constrain the model to generate the JSON output) - [ ] llama-stream. (new APIS `compute_single`, `get_output_single`, `fini_single`) - [ ] llava. (image representation) - [ ] llava-base64-stream. (image representation) - [ ] multimodel. (image representation) - [ ] Target [llamaedge](https://github.com/LlamaEdge/LlamaEdge)		2024-09-10 08:45:18 +08:00
..
debug-engine	Fix warnings/issues reported in Windows and by CodeQL/Coverity (#3275)	2024-04-07 11:57:31 +08:00
lib-pthread	Support more features for rt-thread (#3661)	2024-07-26 10:34:15 +08:00
lib-rats	Clarify how to verify SGX evidence without an Intel SGX-enabled platform (#3158)	2024-02-17 18:44:22 +08:00
lib-socket	Specify language in the wasi socket ext project (#3183)	2024-02-28 19:35:00 +08:00
lib-wasi-threads	Support more features for rt-thread (#3661)	2024-07-26 10:34:15 +08:00
libc-builtin	libc-builtin: Fix function prototype for wasm_runtime_module_realloc (#3702)	2024-08-13 17:44:58 +08:00
libc-emcc	Add emscripten_sleep() wrapper to libc-emcc (#3669)	2024-07-30 10:52:44 +08:00
libc-uvwasi	Refactor APIs and data structures as preliminary work for Memory64 (#3209)	2024-03-12 11:38:50 +08:00
libc-wasi	libc-wasi: Make rights of STDIN/STDOUT/STDERR fixed and overlook their access modes (#3694)	2024-08-13 10:10:22 +08:00
thread-mgr	debug-interp: Only add lock when signal_flag is SIG_SINGSTEP (#3704)	2024-08-14 09:03:01 +08:00
wasi-nn	wasi-nn: Add a new target for llama.cpp as a wasi-nn backend (#3709)	2024-09-10 08:45:18 +08:00