Share the Metal session graph with CUDA for text and vision, MTP and exact sampling, steering, checkpoints, and disk-only BF16 n-grams. Add bounded concurrent Linux n-gram reads, vectorized dense and expert kernels, register-held recurrent prefill state, and efficient small speculative batches.
Keep Qwen out of DeepSeek batch dispatch and exclude disk n-grams from resident memory accounting. Use normal file-backed weight loading in diagnostics and link n-gram support into the CUDA quality scorer.
Include independent kernel and memory-safety tests, mixed-prefill and recovery checks, long-context server and agent coverage, and user documentation with measured DGX Spark performance.
Document the measured README, fresh and continued prefill gains, exact state and continuation checks, memory bounds and agent regression. Include the small automatic-cache decode cost instead of claiming a decoding speedup.
Add bounded SSD streaming, exact short prefills, accelerated large prefills, and native session batching. Support resident tensor parallel inference across two DGX Sparks over RoCE, with aligned expert shards, split vocabulary projection, decode graphs, and shared-expert overlap.
Include primitive, state, transport, and model regression tests, plus usage documentation and measured QA results.
Keep the introduction and everyday usage in the README, with setup guides near the top and detailed references at the end. Document Ada/L40S support explicitly and replace stale model, memory, caching and performance claims.
Retain the root Strix Halo page as a link to its new guide.
Salvatore Sanfilippo