Gahow Wang e1eb77baa4 xserv-chat: fix unclosed <think> on early termination and flush analysis tokens ...

Close the <think> block when EOS or max_tokens interrupts an analysis
channel, and flush stdout after each analysis token so --think streams
smoothly instead of dumping in buffer-sized chunks.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-06-03 01:01:41 +08:00

..

xserv-cuda

cuda: add cached_trim() to release pooled GPU buffers

2026-05-30 12:50:04 +08:00

xserv-distributed

distributed: NCCL P2P primitives (PpContext + send/recv)

2026-05-29 18:45:42 +08:00

xserv-kernels

model: fused GPU MoE kernel — eliminate CPU roundtrip

2026-05-31 13:22:59 +08:00

xserv-model

xserv-chat: fix unclosed <think> on early termination and flush analysis tokens

2026-06-03 01:01:41 +08:00

xserv-server

server: canonical harmony system message in gpt-oss fallback

2026-06-02 15:19:50 +08:00

xserv-tensor

tensor: add narrow() view and relax is_contiguous for size-1 dims

2026-05-30 12:49:57 +08:00

xserv-tokenizer

tokenizer: read pre-tokenizer regex from tokenizer.json

2026-05-31 13:22:35 +08:00