-
Notifications
You must be signed in to change notification settings - Fork 1
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
[Benchmark] Multi-dimensional efficiency & effectiveness measurement framework
enhancementNew feature or requestNew feature or requestharness-opsHarnessOps / AHE loopHarnessOps / AHE loopnvidia-integrationNVIDIA GPU/Skills integrationNVIDIA GPU/Skills integrationperformancePerformance improvementPerformance improvementprefix-kv-cachePrefix KV Cache optimizationPrefix KV Cache optimizationStatus: Open.#58 In DevSecOpsLab-CSIE-NPU/opencode-owl;[NVIDIA #9] Test cases for GPU-agnostic compatibility (CPU-only environment)
enhancementNew feature or requestNew feature or requestgpuGPU hardware accelerationGPU hardware accelerationnvidia-integrationNVIDIA GPU/Skills integrationNVIDIA GPU/Skills integrationStatus: Open.#57 In DevSecOpsLab-CSIE-NPU/opencode-owl;[NVIDIA #8] GPU-agnostic compatibility layer — all features must degrade gracefully without NVIDIA GPU
enhancementNew feature or requestNew feature or requestgpuGPU hardware accelerationGPU hardware accelerationnvidia-integrationNVIDIA GPU/Skills integrationNVIDIA GPU/Skills integrationStatus: Open.#56 In DevSecOpsLab-CSIE-NPU/opencode-owl;[NVIDIA #7] Vertical integration tracking: Application-layer + Hardware-layer Prefix KV Cache
enhancementNew feature or requestNew feature or requestgpuGPU hardware accelerationGPU hardware accelerationnvidia-integrationNVIDIA GPU/Skills integrationNVIDIA GPU/Skills integrationprefix-kv-cachePrefix KV Cache optimizationPrefix KV Cache optimizationStatus: Open.#55 In DevSecOpsLab-CSIE-NPU/opencode-owl;[NVIDIA #6] TensorRT-LLM as ultra-low-latency AHE eval backend on GB10
enhancementNew feature or requestNew feature or requestgpuGPU hardware accelerationGPU hardware accelerationharness-opsHarnessOps / AHE loopHarnessOps / AHE loopnvidia-integrationNVIDIA GPU/Skills integrationNVIDIA GPU/Skills integrationStatus: Open.#54 In DevSecOpsLab-CSIE-NPU/opencode-owl;[NVIDIA #5] GPU-accelerated memory eviction scheduling via cuOpt (replace LRU)
enhancementNew feature or requestNew feature or requestgpuGPU hardware accelerationGPU hardware accelerationnvidia-integrationNVIDIA GPU/Skills integrationNVIDIA GPU/Skills integrationprefix-kv-cachePrefix KV Cache optimizationPrefix KV Cache optimizationStatus: Open.#53 In DevSecOpsLab-CSIE-NPU/opencode-owl;[NVIDIA #4] Integrate NVIDIA AI-Q Blueprint as AHE deep-research analysis backend
enhancementNew feature or requestNew feature or requestharness-opsHarnessOps / AHE loopHarnessOps / AHE loopnvidia-integrationNVIDIA GPU/Skills integrationNVIDIA GPU/Skills integrationStatus: Open.#52 In DevSecOpsLab-CSIE-NPU/opencode-owl;[NVIDIA #3] Upgrade embedding backend: Ollama nomic-embed-text → nv-embed-v2 on GB10
enhancementNew feature or requestNew feature or requestgpuGPU hardware accelerationGPU hardware accelerationnvidia-integrationNVIDIA GPU/Skills integrationNVIDIA GPU/Skills integrationperformancePerformance improvementPerformance improvementStatus: Open.#51 In DevSecOpsLab-CSIE-NPU/opencode-owl;[NVIDIA #2] Add vLLM local backend with RadixAttention prefix caching to AHE eval
enhancementNew feature or requestNew feature or requestgpuGPU hardware accelerationGPU hardware accelerationharness-opsHarnessOps / AHE loopHarnessOps / AHE loopnvidia-integrationNVIDIA GPU/Skills integrationNVIDIA GPU/Skills integrationprefix-kv-cachePrefix KV Cache optimizationPrefix KV Cache optimizationvllmvLLM inference backendvLLM inference backendStatus: Open.#50 In DevSecOpsLab-CSIE-NPU/opencode-owl;[NVIDIA #1] Install NVIDIA Skills into opencode-owl skill registry (P0)
enhancementNew feature or requestNew feature or requestgood first issueGood for newcomersGood for newcomersnvidia-integrationNVIDIA GPU/Skills integrationNVIDIA GPU/Skills integrationStatus: Open.#49 In DevSecOpsLab-CSIE-NPU/opencode-owl;[Prefix-KV #7] Research: Radix Tree memory index for prefix-aware retrieval
enhancementNew feature or requestNew feature or requestprefix-kv-cachePrefix KV Cache optimizationPrefix KV Cache optimizationStatus: Open.#48 In DevSecOpsLab-CSIE-NPU/opencode-owl;[Prefix-KV #6] Anthropic cache_control integration via structured system prompt blocks
enhancementNew feature or requestNew feature or requestprefix-kv-cachePrefix KV Cache optimizationPrefix KV Cache optimizationStatus: Open.#47 In DevSecOpsLab-CSIE-NPU/opencode-owl;