Commit Graph
14 Commits
Author SHA1 Message Date
wmantly ba0aaed7bb feat: integrate xrip/llama.cpp-avx1-numa-sm75 fork with NCCL & NUMA optimizations 2026-09-02 16:02:55 +00:00
wmantly 38b308c6fd Docs: Update README with 38.7-44.6 tok/s decode, 502 tok/s prefill, and 33W cluster idle power benchmarks 2026-09-02 01:04:49 +00:00
wmantly 4a03c75710 Perf: Enable native MTP speculative decoding (draft-n-max 2), achieving 38.73 tok/s (+120% speedup) at 64.8% draft acceptance 2026-09-02 01:00:57 +00:00
wmantly d1353e9b0d Perf: Add cmp-tune insane profile, update Proxmox LXC privileged container docs, and update benchmarks to 28.8 tok/s with PCIe Gen2 and unlocked 610.43.03 driver 2026-09-02 00:56:37 +00:00
wmantly d726501d71 Docs: Add master CMP Reverse Engineering Ecosystem & Community Map (projects, techniques, hardware mods, and AI relevance) 2026-09-02 00:07:59 +00:00
wmantly 53e2b110a9 Enhancement: Integrate NVAPI P8 deep idle downclocking into power governor script 2026-09-02 00:05:23 +00:00
wmantly 3edf469c43 Hardware: Add 20GB modding guide, cmp-pstate NVAPI tool, and document private NvAPI_GPU_SetForcePstate and PCIe retrain mechanisms 2026-09-02 00:02:24 +00:00
wmantly d51de0df6a Docs: Add cluster power optimization benchmark table and Linux headless power management guidelines 2026-09-01 19:31:56 +00:00
wmantly 2a21eae435 Hardware: Add MSI CMP 50HX VBIOS ROM and document the 100% Video Engine Pinning bug and cross-flash idle power drop 2026-09-01 19:24:00 +00:00
wmantly 5f261c191f Docs: Update HARDWARE_LEARNINGS and README with low-latency NCCL ring buffer benchmarks and speculative decoding findings 2026-09-01 16:06:32 +00:00
wmantly 261631457c Update start-server.sh with validated ngram context-lookup speculation and NCCL pipeline flags 2026-09-01 15:56:43 +00:00
wmantly 2b4e826437 Add sglang-inspired low-latency NCCL ring buffer and CUDA connection optimization flags to start-server.sh 2026-09-01 14:55:56 +00:00
wmantly c30f4772f9 Fix power governor active retention during long prompt evaluations and remove redundant proxy governor thread 2026-09-01 14:40:19 +00:00
wmantly aeb72cecfa Initial commit: Complete deployment scripts, power governor, systemd units, and architecture documentation for Turing multi-GPU LLM rig 2026-09-01 01:55:19 +00:00