TensorRT-LLMs/tensorrt_llm/serve
Zheng Duan e831673f80
fix: timeout and broken pipe in disagg and worker tests (#5827)
Signed-off-by: zhengd-nv <200704041+zhengd-nv@users.noreply.github.com>
2025-07-11 12:42:47 +08:00
..
scripts feat: Add no_kv_cache_reuse option and streaming support for trtllm serve bench (#4971) 2025-06-18 13:37:31 +08:00
__init__.py Update TensorRT-LLM (#2820) 2025-02-25 21:21:49 +08:00
chat_utils.py [TRTLLM-5053] Refactoring and Unifying the Multimodal input preparation (#4506) 2025-06-03 12:02:07 -07:00
metadata_server.py feat: Add integration of etcd (#3738) 2025-06-03 20:01:44 +08:00
openai_disagg_server.py fix: timeout and broken pipe in disagg and worker tests (#5827) 2025-07-11 12:42:47 +08:00
openai_protocol.py [nvbug 5004744][fix] rewrite completion API to avoid repetitive tokens (#5201) 2025-07-07 15:06:49 +09:00
openai_server.py [nvbug 5004744][fix] rewrite completion API to avoid repetitive tokens (#5201) 2025-07-07 15:06:49 +09:00
postprocess_handlers.py feat: add deepseek-r1 reasoning parser to trtllm-serve (#3354) 2025-05-06 08:13:04 +08:00
router.py feat: Add integration of etcd (#3738) 2025-06-03 20:01:44 +08:00