Martin Evans
Martin Evans
This PR adds support for async-wasm (see [async.h](https://docs.wasmtime.dev/c-api/async_8h.html)). Async support was added to the C API in https://github.com/bytecodealliance/wasmtime/pull/7106 which has not yet made it into a main wasmtime release, so...
# Prerequisites Please answer the following questions for yourself before submitting an issue. - [x] I am running the latest code. Development is very rapid so there are no tagged...
As briefly discussed in Discord, this modifies the `CommandBuffer` to not return fake `Entity` objects. Instead it returns a `PendingEntity`. This makes the API less confusing and prevents all the...
CryptState.Decrypt (used on line 87 of MumbleConnection.cs) always returns null because some internal checksumming does not work. There's presumably a bug in the implementation of the decryption.
I'm using llama.cpp as a library from C# ([LLamaSharp](https://github.com/SciSharp/LLamaSharp)). If I set a log callback with `llama_log_set` that captures _most_ of the output, so that I can suppress it or...
See comments starting here for previous discussion: https://github.com/SciSharp/LLamaSharp/commit/c325ac91279428e8d88719357b93e43cd9c5ed52#commitcomment-141108660. Ping @zsogitbe. I've been looking into the embeddings issue discuvered by @zsogitbe. In the April update there has been a change to...
Currently the CUDA libraries are built with one particular AVX level (it's not specified in the build script, so whatever the default is). This means that models split between GPU...
Tracking issue for thread safety in llama.cpp. The global inference lock can be removed once this is resolved. https://github.com/ggerganov/llama.cpp/issues/3960
https://github.com/guidance-ai/guidance/blob/main/notebooks/art_of_prompt_design/prompt_boundaries_and_token_healing.ipynb
My game creates and destroys multiple world (running lots of mini-games in sequence). I've found that for the first World everything works fine, but for subsequent games any **static** queries...