-
RioTinto
- Perth, Australia
-
21:16
(UTC +08:00) - https://covfefe.au/
- @Kr4cKHe4D
Highlights
Pinned Loading
-
local-llm-benchmarks
local-llm-benchmarks PublicMeasured llama.cpp benchmarks on AMD Radeon RDNA4 with ROCm: RX 9070 XT + Radeon AI PRO R9700 (48 GB). Qwen3.8, Gemma 4, GLM, gpt-oss; GGUF quant quality (KLD), MTP speculative decoding, 128K conte…
-
dense-moe-research
dense-moe-research PublicCan a dense LLM be made sparse for faster local inference? Converting Qwen3.5-9B FFNs into Mixture-of-Experts, with Triton kernels on AMD RDNA4 (ROCm), benchmarked by KL divergence against llama.cp…
Python
-
-
NFSIISE
NFSIISE PublicForked from zaps166/NFSIISE
Need For Speed™ II SE - Cross-platform wrapper with 3D acceleration and TCP protocol!
Assembly
-
NLP-Examples
NLP-Examples PublicA collection of Python scripts demonstrating how to run various AI tasks locally using models from the Hugging Face Hub and the transformers library (along with related libraries like datasets, sen…
Python 2
-
If the problem persists, check the GitHub status page or contact support.




