SIGN IN SIGN UP
4 branches
.devops
.gemini
.github
.pi
app
benches
benchmark-results
ci
cmake
common
conversion
docs
examples
ggml
gguf-py
grammars
include
licenses
media
models
pocs
profiles
requirements
scripts
skills
src
tests
tools
vendor
.clang-format
.clang-tidy
.dockerignore
.ecrc
.editorconfig
.flake8
.gitignore
.gitmodules
.pre-commit-config.yaml
1
AGENTS.md
ARCHITECTURE.md
AUTHORS
autotune
CLAUDE.md
CMakeLists.txt
CMakePresets.json
CODEOWNERS
COMPILER_OPTIMIZATION_ANALYSIS.md
CONTRIBUTING.md
convert_hf_to_gguf_update.py
convert_hf_to_gguf.py
convert_llama_ggml_to_gguf.py
convert_lora_to_gguf.py
download-lfm25-8b-a1b.sh
download-ornith-35b.sh
flake.nix
FREETOKEN_GTX1080_HANDOFF.md
GTX1080_HANDOFF.md
HYBRID_ANALYSIS.md
HYBRID_ATTRIBUTION.md
HYBRID_DESIGN.md
HYBRID_EXPERIMENTS.md
IGPU_LAYER_EXPERIMENTS.md
IK_LLAMA_EXPERIMENTS.md
KVFLASH_PLAN.md
LICENSE
Makefile
mypy.ini
NOTICE
PREFILL_PLAN.md
pyproject.toml
pyrightconfig.json
README.md
requirements.txt
ROUTER_LOOKAHEAD_ANALYSIS.md
ROUTER_LOOKAHEAD_DESIGN.md
ROUTER_LOOKAHEAD_EXPERIMENTS.md
router1080.sh
router1660.sh
SECURITY.md
start-gemma4-26b-a4b.sh
start-lfm25-8b-a1b.sh
start-ling-tiny-1080.sh
start-ling-tiny.sh
start-ornith.sh
start-turbollm.sh
start.sh
start1080.sh
START1660_REFERENCE.md
start1660.sh
TRANSIENT_EXPERT_ANALYSIS.md
TRANSIENT_EXPERT_DESIGN.md
TRANSIENT_EXPERT_EXPERIMENTS.md
TURBOQUANT_ANALYSIS.md
TURBOQUANT_ATTRIBUTION.md
TURBOQUANT_DESIGN.md
TURBOQUANT_EXPERIMENTS.md
ty.toml