amd-inference

Episodes (6)

Trajectory notes

• 2026-09-10T01:26:25Z: vllm-amd-speculative-decoding closed (faded) — This is an adjacent optimization to Scott’s hardware-aware local inference practice, but the supplied hits establish CUDA/Ollama use rather than an AMD/vLLM deployment, and the grounding supplies no measured latency gains that woul
• 2026-09-04T23:31:00Z: voxgen-vulkan-amd-tts closed (faded) — Scott already maintains a local speech-engine laboratory and self-hosted GPU model zoo, while his Hardware-aware local inference page explicitly treats accelerator placement and runtime policy as engineering concerns. VoxGen could extend t
• 2026-08-27T15:42:57Z: netra-amdgcn-inference-kernels closed (faded) — Scott’s Capability Audit and Discussed Is Not Deployed pages already require independent, representative evidence before upgrading runtime performance or portability claims, while Hardware-aware local inference makes accelerator-s
• 2026-08-20T11:29:14Z: vllm-rocm-rdna2-native-windows closed (faded) — The release extends Scott’s hardware-aware local-inference work with a potential native-Windows AMD alternative to his current WSL2/CUDA substrate, while its conflicting throughput claims and missing replication directly call for