diff --git a/docs/Dankclaw System Specs.md b/docs/Dankclaw System Specs.md index 0810c4f..7f5a8c0 100644 --- a/docs/Dankclaw System Specs.md +++ b/docs/Dankclaw System Specs.md @@ -3,7 +3,7 @@ ## Server Overview Dankclaw is an AMD APU server for vLLM inference. The host runs Ubuntu 26.04 with an AMD Ryzen AI MAX+ 395 Strix Halo APU. The APU uses unified memory — CPU and GPU share the same 61 GB RAM pool. - +rr ## Hardware Specifications ### CPU diff --git a/docs/README.md b/docs/README.md deleted file mode 100644 index d064eb9..0000000 --- a/docs/README.md +++ /dev/null @@ -1,26 +0,0 @@ -# vLLM Scripts — Knowledge Base - -Documentation for running vLLM inference on two local machines. - -## Servers - -| Server | GPU | VRAM / Memory | OS | -|--------|-----|---------------|------| -| [[Dankserver System Specs\|Dankserver]] | NVIDIA RTX 3090 | 24 GB VRAM, 62 GB RAM | Ubuntu 24.04 | -| [[Dankclaw System Specs\|Dankclaw]] | AMD Radeon 8060S (Strix Halo) | 61 GB unified | Ubuntu 26.04 | - -## vLLM Reference - -- [[VLLM Overview]] — installation, CLI, API, architecture, quantization, parallelism -- [[VLLM Index]] — quick reference with commands, endpoints, and parameter table - -## Memory Management - -- [[RAM CPU Offloading in VLLM]] — KV cache swap between GPU VRAM and system RAM -- [[Hybrid CPU GPU Processing Dankserver]] — NVIDIA GPU compute with system RAM offload -- [[Shared Memory Architecture Dankclaw]] — AMD unified memory and ROCm configuration - -## Model Deployment - -- [[Running Qwen3.6 35B A3B FP8 on Dankserver]] — MoE model (35B total, 3B active) on RTX 3090 -- [[Running Qwen3.6 27B FP8 on Dankclaw]] — Dense model (27B) on Strix Halo APU diff --git a/docs/index.md b/docs/index.md index d064eb9..3b78000 100644 --- a/docs/index.md +++ b/docs/index.md @@ -4,10 +4,10 @@ Documentation for running vLLM inference on two local machines. ## Servers -| Server | GPU | VRAM / Memory | OS | -|--------|-----|---------------|------| -| [[Dankserver System Specs\|Dankserver]] | NVIDIA RTX 3090 | 24 GB VRAM, 62 GB RAM | Ubuntu 24.04 | -| [[Dankclaw System Specs\|Dankclaw]] | AMD Radeon 8060S (Strix Halo) | 61 GB unified | Ubuntu 26.04 | +| Server | GPU | VRAM / Memory | OS | +| --------------------------------------- | ----------------------------- | --------------------- | ------------ | +| [[Dankserver System Specs\|Dankserver]] | NVIDIA RTX 3090 | 24 GB VRAM, 62 GB RAM | Ubuntu 24.04 | +| [[Dankclaw System Specs\|Dankclaw]] | AMD Radeon 8060S (Strix Halo) | 61 GB unified | Ubuntu 26.04 | ## vLLM Reference