antirez 97ba327538 Read Qwen native BF16 n-grams directly from the GGUF ...

Keep the table outside model mappings and Metal residency. Use bounded explicit reads, reject failed lookups before GPU consumption, and remove the runtime sidecar option and paging controls. Preserve Qwen hash and speculative state handling; cover malformed files and exact recovery after prefill, decode, and MTP read failures.

2026-09-14 13:32:48 +02:00

..

build_direction.py

Read Qwen native BF16 n-grams directly from the GGUF

2026-09-14 13:32:48 +02:00

run_sweep.py

Add verbosity steering example

2026-05-11 10:50:39 +02:00