Kunshang Ji ca21483bf9 [MISC] fix pin_memory=torch.cuda.is_available(), use is_pin_memory_available (#37415) ...

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

2026-03-19 09:23:24 +00:00

..

__init__.py

[Perf] Optimize Python Slice for Structured Output using islice instead of [:] (#33593)

2026-02-24 09:02:36 -08:00

backend_guidance.py

[FIX] guidance: use max(vocab_size, len(tokenizer)) for n_vocab (#33509)

2026-02-06 14:23:03 +00:00

backend_lm_format_enforcer.py

[MISC] fix pin_memory=torch.cuda.is_available(), use is_pin_memory_available (#37415)

2026-03-19 09:23:24 +00:00

backend_outlines.py

[MISC] fix pin_memory=torch.cuda.is_available(), use is_pin_memory_available (#37415)

2026-03-19 09:23:24 +00:00

backend_types.py

[Misc] Refactor tokenizer interface (#29693)

2025-11-29 04:02:21 -08:00

backend_xgrammar.py

[Feature] Lazy import for the "mistral" tokenizer module. (#34651)

2026-02-23 00:43:01 -08:00

request.py

[Minor] Various small code cleanups/simplifications (#31508)

2025-12-29 22:42:06 -08:00

utils.py

[Bugfix] Fix xgrammar dtype mismatch on macOS CPU inference (#32384)

2026-03-14 17:29:06 +00:00