Jiejing 54bbcd7cdf Merge openai-server (#147) into pd-split: prompt tokenizer; pd_server takes the --tokenizer-* flags ... Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01YNgkNrJL5oR1pZqVYzZMHW		2026-10-23 05:34:26 +00:00
..
distributed	initial commit	2026-10-20 12:09:42 +08:00
engine	initial commit	2026-10-20 12:09:42 +08:00
hicache	Add a host-memory prefix cache (HiCache-style) for the offline engine	2026-10-21 22:26:29 +00:00
models	initial commit	2026-10-20 12:09:42 +08:00
serve	serve: exact fast prompt tokenization (fastokens or added-token segment cache), checked against tokenizer.encode	2026-10-23 03:50:06 +00:00
ve	initial commit	2026-10-20 12:09:42 +08:00
worker	initial commit	2026-10-20 12:09:42 +08:00
__init__.py	initial commit	2026-10-20 12:09:42 +08:00
conftest.py	initial commit	2026-10-20 12:09:42 +08:00
test_cuda_sync_guards.py	initial commit	2026-10-20 12:09:42 +08:00