Grammar-forced speculative drafts: GBNF grammar as a third draft source, guaranteed-accepted forced spans, lossless + opt-in (#48, #70)

New byte-level GBNF-subset engine (c/grammar.h: parser + set-of-stacks PDA
walker) wired into spec_decode as a third draft source ("metodo F"), tried
before MTP/n-gram. Wherever the grammar admits exactly one legal byte, the
forced span is tokenized and injected as drafts; the existing batch-union
verification confirms them, so a wrong or out-of-sync grammar can never
change the output. Lazy arming skips preambles; adaptive guard (same
pattern as MTP) disables the source below 50% acceptance; grammar-accepted
tokens no longer pollute the MTP acceptance counter.

GRAMMAR=file.gbnf enables it in run and serve modes (also with DRAFT=0 and
with the int4 MTP head from #8); GRAMMAR_DRAFT=n caps the span (default 24).

Measured on M3 Max / int8-MTP container, greedy, MTP=0 DRAFT=0, NDJSON
classification: 0.37 -> 0.50 tok/s (1.60 tok/forward, 81 fw per 130 tok),
100% acceptance (48/48), output byte-identical to baseline.

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

.gitignore

@@ -16,6 +16,8 @@ c/backend_cuda.o
 c/backend_cuda_test
 c/tests/test_json
 c/tests/test_st
+c/tests/test_tier
+c/tests/test_grammar
 
 # oracoli tiny generati (make_glm_oracle.py) e dati benchmark scaricati
 c/glm_tiny/