Jetson Nano edge AI vision Agent Harness: real-time video analytics, MCP tools, event evidence, DeepSeek online/offline, secure recovery
alphaparkinc/genpark-speculative-decoding-draft-acceptance-evaluator-skillGenPark AI Agent Skill - Rejection sampling and logit verification engine for speculative decoding acceleration.
Alpha-Park/genpark-paged-attention-kv-cache-block-allocator-skillGenPark AI Agent Skill - Simulates vLLM PagedAttention non-contiguous virtual memory block table allocation for dynamic KV-cache management.
alphaparkinc/genpark-multi-gpu-tensor-parallel-sharding-planner-skillGenPark AI Agent Skill - Calculates tensor parallelism column and row weight matrix partition splits across distributed GPU clusters.
Alpha-Park/genpark-speculative-decoding-draft-acceptance-evaluator-skillGenPark AI Agent Skill - Rejection sampling and logit verification engine for speculative decoding acceleration.
alphaparkinc/genpark-gguf-tensor-metadata-header-validator-skillGenPark AI Agent Skill - Validates GGUF/GGML model binary headers, tensor alignment, KV-cache parameters and architecture keys.
Alpha-Park/genpark-weight-quantization-kquants-block-packer-skillGenPark AI Agent Skill - Simulates k-quants block compression (Q4_K_M, Q8_0) packing FP16 weights into quantized blocks with scale factors.
Alpha-Park/genpark-multi-gpu-tensor-parallel-sharding-planner-skillGenPark AI Agent Skill - Calculates tensor parallelism column and row weight matrix partition splits across distributed GPU clusters.
alphaparkinc/genpark-weight-quantization-kquants-block-packer-skillGenPark AI Agent Skill - Simulates k-quants block compression (Q4_K_M, Q8_0) packing FP16 weights into quantized blocks with scale factors.
alphaparkinc/genpark-paged-attention-kv-cache-block-allocator-skillGenPark AI Agent Skill - Simulates vLLM PagedAttention non-contiguous virtual memory block table allocation for dynamic KV-cache management.
Alpha-Park/genpark-gguf-tensor-metadata-header-validator-skillGenPark AI Agent Skill - Validates GGUF/GGML model binary headers, tensor alignment, KV-cache parameters and architecture keys.
alphaparkinc/genpark-speculative-decoding-verifier-skillDraft-target model speculative decoding verification engine with rejection sampling, acceptance rate telemetry, and dynamic speedup ratio estimation.
Alpha-Park/genpark-speculative-decoding-verifier-skillDraft-target model speculative decoding verification engine with rejection sampling, acceptance rate telemetry, and dynamic speedup ratio estimation.
alphaparkinc/genpark-kv-cache-paged-attention-allocator-skillVirtual paged attention KV-cache memory manager with logical block mapping, non-contiguous physical page allocation, and zero-copy fragmentation tracking.
Alpha-Park/genpark-int8-symmetric-per-tensor-quantizer-skillSymmetric INT8 per-tensor and per-channel quantization engine for LLM weights and activations, with SNR and MSE reconstruction telemetry.
alphaparkinc/genpark-edge-inference-latency-telemetry-skillHigh-precision edge and on-device LLM inference profiler calculating TTFT, TPOT, tokens/second throughput, and percentile jitter distributions (P50/P90/P99).
Alpha-Park/genpark-edge-inference-latency-telemetry-skillHigh-precision edge and on-device LLM inference profiler calculating TTFT, TPOT, tokens/second throughput, and percentile jitter distributions (P50/P90/P99).
fxd0h/Axelera-Voyager-Local-AssistantLocal AI assistant for the Axelera Voyager SDK and Metis AIPU — semantic RAG over the public Axelera sources + workflow skills, via MCP. No account, no cloud.