Popular repositories Loading
-
exllamav3
exllamav3 PublicForked from turboderp-org/exllamav3
ExLlamaV3 with Turing (sm_75) fast paths for RTX 20xx / 2080 Ti 22 GB: flash-attention prefill, 4-bit cache flash-decoding, GDN kernels. See doc/turing.md
Python
-
Strata
Strata PublicForked from Niko1221/Strata
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
C++
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.