TensorRT-LLMs/tensorrt_llm/serve
2025-12-16 05:16:32 -08:00
..
scripts [None][feat] support for more accurate AR calculation (#9323) 2025-11-29 00:34:21 +08:00
tool_parser [TRTLLM-9637][feat] Support tool parser for Kimi K2 (#9830) 2025-12-12 23:32:39 +08:00
__init__.py Update TensorRT-LLM (#2820) 2025-02-25 21:21:49 +08:00
chat_utils.py [None][feat] Support custom chat template for tool calling (#9297) 2025-11-25 22:07:04 +08:00
cluster_storage.py [TRTLLM-8431][doc] update public doc and example, add etcd auto-scaling tests (#8602) 2025-10-28 17:04:53 -07:00
disagg_auto_scaling.py [TRTLLM-9181][feat] improve disagg-server prometheus metrics; synchronize workers' clocks when workers are dynamic (#9726) 2025-12-16 05:16:32 -08:00
harmony_adapter.py [https://nvbugs/5521799][fix] Trim incorrectly generated harmony messages (#7849) 2025-09-24 16:38:43 +08:00
metadata_server.py feat: Add integration of etcd (#3738) 2025-06-03 20:01:44 +08:00
openai_client.py [TRTLLM-9181][feat] improve disagg-server prometheus metrics; synchronize workers' clocks when workers are dynamic (#9726) 2025-12-16 05:16:32 -08:00
openai_disagg_server.py [TRTLLM-9181][feat] improve disagg-server prometheus metrics; synchronize workers' clocks when workers are dynamic (#9726) 2025-12-16 05:16:32 -08:00
openai_disagg_service.py [TRTLLM-9468][chore] Update disagg benchmarking scripts to support context parallelism (#9720) 2025-12-12 22:29:41 -08:00
openai_protocol.py [TRTLLM-9736][feat] AsyncLLM and verl integ (#9353) 2025-12-11 09:33:25 -08:00
openai_server.py [None][feat] Support Mistral Large3 LLM part (#9820) 2025-12-13 11:44:27 +08:00
openai_service.py [TRTLLM-8920][feat] decouple disagg service from fastapi (#8714) 2025-12-05 10:44:16 +08:00
perf_metrics.py [TRTLLM-9181][feat] improve disagg-server prometheus metrics; synchronize workers' clocks when workers are dynamic (#9726) 2025-12-16 05:16:32 -08:00
postprocess_handlers.py [None][feat] Update reasoning parser for nano-v3 (#9944) 2025-12-15 05:39:37 -08:00
responses_utils.py [TRTLLM-8920][feat] decouple disagg service from fastapi (#8714) 2025-12-05 10:44:16 +08:00
router.py [TRTLLM-9181][feat] improve disagg-server prometheus metrics; synchronize workers' clocks when workers are dynamic (#9726) 2025-12-16 05:16:32 -08:00