Popular repositories Loading
-
-
cve-ptrace-mm-null-block
cve-ptrace-mm-null-block PublicSystemTap mitigation for __ptrace_may_access mm==NULL privilege escalation
Python 2
-
-
-
llama-moe-hybrid-tuning
llama-moe-hybrid-tuning PublicBackend-agnostic llama.cpp tuning for large MoE models on small-VRAM GPUs (experts-on-CPU hybrid): ~8-14x prefill via --no-mmap + batch/THP/boost. Helps AMD/NVIDIA/Intel.
Shell 1
-
mi210-llm-stack
mi210-llm-stack PublicAMD MI210 (gfx90a/CDNA2) LLM inference optimization — TurboQuant, KIVI, per-layer KV types, FlashAttention, MoE expert caching
Python 1
If the problem persists, check the GitHub status page or contact support.




