TensorRT-LLMs/tensorrt_llm/executor
Yechan Kim 8b4104d34a
feat: add HyperCLOVAX-SEED-Vision support in refactored way (#4799)
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
2025-06-09 11:04:04 +08:00
..
__init__.py chore: rename ExecutorBindingsWorker/Proxy (#4716) 2025-05-29 10:32:35 +08:00
executor.py chore: rename ExecutorBindingsWorker/Proxy (#4716) 2025-05-29 10:32:35 +08:00
ipc.py fix [nvbug5256044]: bench hang due to llmapi ipc (#4798) 2025-06-03 10:10:53 +08:00
postproc_worker.py fix: [nvbugs/5066257] serialization improvments (#3869) 2025-05-23 13:06:29 +08:00
proxy.py chore: remove request_error ipc in LLM.submit (#4763) 2025-06-03 20:55:59 +08:00
request.py feat: Add multimodal embedding field in LlmRequest (#3855) 2025-05-01 12:23:30 +08:00
result.py Refactor the first token response in PD (#4692) 2025-06-04 09:11:23 +08:00
serialization.py feat: add HyperCLOVAX-SEED-Vision support in refactored way (#4799) 2025-06-09 11:04:04 +08:00
utils.py chore: remove request_error ipc in LLM.submit (#4763) 2025-06-03 20:55:59 +08:00
worker.py [AutoDeploy] _AutoDeployLlmArgs as primary config object (#4891) 2025-06-05 17:20:55 +08:00