Cleared 4m ago · ggml-org/llama.cpp #17488 · C++ · ★ 125k · MIT
Hey there! I am trying to convert my fine-tuned vibevoice into a gguf format for inference but cant find proper code or converter any where. The architecture is currently unsupported to any known converter like llama.cpp but I have already seen many variation of gguf-formated…
#77 · C++ · ★ 41 · GPL-3.0 · updated 2d ago
Code Review — ingame_overlay Date: 2026-08-19 Scope: Core library (src/, include/, public/ — ~17k lines, 52 files). Vendored deps (ImGui, mini_detour, glad2, VulkanSDK headers) and test harnesses excluded. Depth: "standard" — all core files read; Windows DX9/11/12, Vulkan,…
#3406 · C++ · ★ 205 · GPL-3.0 · updated 10d ago
Two minor follow-ups split out from the review of #3281 (now merged as e68f445f). Both are low-priority polish items, not blockers — filing them so they don't get lost. cc @jensenpat — these came out of the review of your release-asset PR; tagging you since you have the context…
#505 · C++ · ★ 1.6k · MIT · updated 12d ago
This is a demo of how it works, you should write the probe in eBPF, and add it to https://github.com/eunomia-bpf/bpftime/tree/master/example/gpu and make sure user don't need to modify their program to do the tracing. Program 2: Per-thread runtime distribution using clock64()…
#3361 · C++ · ★ 832 · BSD-3-Clause · updated 13h ago
To facilitate working with the sum-to-zero constraint in multivariate contexts, it would be valuable to be able to specify not only individual sum_to_zero_vectors but also matrices for which all rows or all columns are constrained to sum to zero. To my knowledge, there is no…