Here are
23 public repositories
matching this topic...
LLM speculative inference server for heterogeneous hardware & consumer GPUs
The fastest vLLM build for AMD R9700's. For the latest updates join the Launch80 discord server. I am on X now also https://x.com/bkuyper
Updated
Oct 1, 2026
Python
Working on the fastet vllm path for AMD Radeon AI PRO R9700
Updated
Oct 5, 2026
Python
vLLM for AMD RDNA4 (gfx1201): Radeon AI PRO R9700 & RX 9070 XT — native MXFP4 linear kernel + spec-decode verify fix, carried as rebased branches (fork-carry model)
Updated
Sep 3, 2026
Python
WHIRL (Windows HIP Inference for RDNA LLMs): native Windows C++/HIP LLM inference engine for the AMD Radeon AI PRO R9700
App to handle one GPU to multiple models/element with queuing and log tracking all with a local hosted web dashboard
Reproducible diagnostics, patches, and validation evidence for AMD GPU Direct P2P on Intel X99 / Broadwell-EP, with RCCL and SGLang/Qwen3.8 case studies.
Updated
Sep 28, 2026
Shell
Experimental ROCm 10 compatibility build for Qwen3.8-Flash-Next on 4x AMD R9700
Updated
Sep 8, 2026
Dockerfile
The unmodified upstream Linux amdgpu + amdkfd driver running on macOS: AMD Radeon GPUs over Thunderbolt on Apple Silicon, inside a DriverKit extension.
HyperLoom R9700 R&D hub for reproducible AMD/ROCm agentic-infrastructure experiments with explicit evidence and truth boundaries.
Updated
Sep 25, 2026
Python
Minimal AITER LDS and ROCr idle-CPU fixes for Radeon AI PRO R9700 on vLLM 0.29.0 / ROCm 7.2.3
Updated
Oct 2, 2026
Shell
Verified dual-R9700 deployment recipe, configs, scripts, and benchmarks for Dyluhn/R9V Qwen3.8 Flash-Next
Updated
Sep 2, 2026
Shell
Instrumented AMD R9700 inference with numerical alignment, qualified performance backports, persistent chat snapshots and Pi integration. Downstream of Radiance.
Updated
Oct 3, 2026
Python
HyperLoom R9700 experiment: minimal container/runtime baseline for reproducible AMD/ROCm validation. Not a standalone product.
Updated
Sep 4, 2026
Python
HyperLoom R9700 experiment: provider bridge validation against the local AMD execution fabric. Not a standalone product.
Updated
Sep 4, 2026
Python
HyperLoom R9700 probe: evidence-reader validation for auditable AMD/local executions. Not a standalone product.
Updated
Sep 4, 2026
Python
HyperLoom R9700 experiment: bounded autonomous-loop validation with evidence and failure boundaries. Not a standalone product.
Updated
Sep 4, 2026
Python
HyperLoom R9700 probe: isolated tool-contract validation for the InnerOS AMD research line. Not a standalone product.
Updated
Sep 4, 2026
Python
HyperLoom R9700 probe: bounded bridge smoke test for the AMD/local execution fabric. Not a standalone product.
Updated
Sep 4, 2026
Python
HyperLoom R9700 probe: minimal agent execution smoke test on the AMD/local runtime. Not a standalone product.
Updated
Sep 4, 2026
Python
Add this topic to your repo
To associate your repository with the
r9700
topic, visit your repo's landing page and select "manage topics."
Learn more
You can’t perform that action at this time.