Block a user
Implement the Qwen3.8 Flash Next Rust and Metal text core
Implement the Qwen3.8 Flash Next Rust and Metal text core
Implemented in c414640 (Implement Qwen text core).\n\nThe server now opens the frozen Qwen safetensors set through a dedicated Rust model/executor path and runs the 48-layer 3:1 hybrid text graph…
Integrate Qwen3.8 Flash Next loading and tokenizer behavior
Integrate Qwen3.8 Flash Next loading and tokenizer behavior
Implemented and verified in commit 3773cfd (Integrate Qwen3.8 model intake).\n\nThe native model catalog and Model Manager now treat the pinned 29-file, 105,438,842,430-byte Bare Speed set as one…
Prepare exact Qwen3.8 Flash Next Bare Speed artifacts
Prepare exact Qwen3.8 Flash Next Bare Speed artifacts
Implemented and pushed as commit 4c83ac0.
The repository now contains a Rust-only qwen38-artifacts tool plus an immutable manifest and complete 2,527-tensor inventory for Youssofal/Qwen3.8-Flash-N…
Optimize and benchmark Qwen3.8 Flash Next on Apple silicon
Add Qwen3.8 Flash Next native MTP speculation
Implement exact Qwen Sparse Attention and long-context state
Stream Qwen3.8 Flash Next PLE from mapped storage
Implement the Qwen3.8 Flash Next Rust and Metal text core
Define Qwen3.8 Flash Next artifacts and model contract