ruihan 48a1c9d7c4 Record successful 2048-token CUDA Graph retest and preserve failure samples

2026-09-17 23:04:40 +08:00

..

results

Record successful 2048-token CUDA Graph retest and preserve failure samples

2026-09-17 23:04:40 +08:00

architecture.md

Enable validated prefix caching and record DGX Spark optimization benchmarks

2026-09-17 22:09:58 +08:00

benchmark-method.md

Record successful 2048-token CUDA Graph retest and preserve failure samples

2026-09-17 23:04:40 +08:00

cuda-graph-retest.md

Record successful 2048-token CUDA Graph retest and preserve failure samples

2026-09-17 23:04:40 +08:00

optimization-results.md

Record successful 2048-token CUDA Graph retest and preserve failure samples

2026-09-17 23:04:40 +08:00

packaging-validation.md

Enable validated prefix caching and record DGX Spark optimization benchmarks

2026-09-17 22:09:58 +08:00

provenance.md

Enable validated prefix caching and record DGX Spark optimization benchmarks

2026-09-17 22:09:58 +08:00

troubleshooting.md

Add reproducible DGX Spark deployment for Qwen3.8 Flash Next NVFP4

2026-09-17 16:45:50 +08:00

validation.md

Add reproducible DGX Spark deployment for Qwen3.8 Flash Next NVFP4

2026-09-17 16:45:50 +08:00