llama-cpp: llama-server with DFlash2 speculative decoding for gfx1151
v0.8.0 is the first upstream release with DFlash2 drafters; nixpkgs has 0.6.0 (unstable) and an older tree (stable), so the engine is built here. HIP build for Strix Halo. The NixOS module exposes llama-server behind skyg.nixos.server.services.llama-cpp; fwdesk wires it to Qwen3.8-27B + its DFlash2 drafter, disabled until the weights are on disk.
This commit is contained in:
1 parent
62c41a6f8e
commit
ce92096042
9 files changed
+392
No files matched your search
@@ -4,6 +4,7 @@
|
||||
./audiobookshelf.nix
|
||||
./ai-services.nix
|
||||
./colibri.nix
|
||||
./llama-cpp.nix
|
||||
./comfyui
|
||||
./jellyfin.nix
|
||||
./nbot-agent.nix
|
||||
|
||||
Reference in new issue
Block a user