deepjavalibrary djl-serving issues

deepjavalibrary / djl-serving

A universal scalable machine learning model deployment solution

Apache License 2.0

199 stars 67 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

[0.31.0-dlc] Fix parsing adapters list in inference request

#2600 xyang16 closed 12 hours ago
0
Enable llama instruct models test cases in benchmark testing

#2599 lxning closed 16 hours ago
0
[lora] Fix lora integration test

#2598 xyang16 closed 19 hours ago
0
Update config file to activate more test cases

#2597 lxning closed 17 hours ago
0
[0.31.0-dlc] Fix lora integration test

#2596 xyang16 closed 19 hours ago
0
[lora] Log adapter name in inference

#2595 xyang16 closed 21 hours ago
0
[0.31.0-dlc] Log adapter name in inference

#2594 xyang16 closed 22 hours ago
0
[0.31.0-dlc] [fix] Fix input request adapter parsing

#2593 xyang16 closed 23 hours ago
0
[fix] Fix input request adapter parsing

#2592 xyang16 closed 23 hours ago
0
[docker][lmi] reduce number of layers by consolidating some commands

#2591 siddvenk opened 1 day ago
0
[docker] fix typo in install_djl_serving script

#2590 siddvenk closed 1 day ago
0
Refactor LMI dockerfile (#2576)

#2589 siddvenk closed 20 hours ago
1
[doc] add neuron release notes and update user guide doc

#2588 sindhuvahinis opened 1 day ago
0
[doc] add neuron release notes and update user guide doc

#2587 sindhuvahinis closed 1 day ago
0
[python] remove huggingface load and save for tnx (#2499)

#2586 sindhuvahinis closed 1 day ago
0
[cherry-pick][lmi] validate inputs field is of type string for request (#2583)

#2585 siddvenk closed 2 days ago
0
Create sheteng-test.yml for test

#2584 HappyAmazonian closed 2 days ago
0
[lmi] validate inputs field is of type string for request

#2583 siddvenk closed 2 days ago
0
[docker] update neuron artifacts to 2.20.1 (#2577)

#2582 sindhuvahinis closed 2 days ago
0
[docker] update neuron artifacts to 2.20.1 (#2577)

#2581 sindhuvahinis closed 2 days ago
0
[cherry-pick][fix][ci] specify guaranteed_no_evict batch_scheduler_policy to get t…

#2580 sindhuvahinis closed 2 days ago
0
[cherry-pick][fix][ci] specify guaranteed_no_evict batch_scheduler_policy to get t…

#2579 sindhuvahinis closed 2 days ago
0
Bump DJL version to 0.32.0-SNAPSHOT

#2578 siddvenk closed 2 days ago
1
[docker] update neuron artifacts to 2.20.1

#2577 sindhuvahinis closed 2 days ago
0
Refactor LMI dockerfile

#2576 siddvenk closed 1 day ago
0
[0.30.0 dlc][cherry-pick] legacy partition removal and add on_device_embedding true

#2575 sindhuvahinis closed 3 days ago
0
add workflow sagemaker_llm_benchmark back

#2574 lxning closed 3 days ago
0
[cherry-pick][0.30.0-dlc][test] fix transformers neuronx integration test failure (#2539)

#2573 sindhuvahinis closed 3 days ago
0
[0.30.0-dlc] upgrade neuron vllm to 0.6.2

#2572 sindhuvahinis closed 3 days ago
0
remove sagemaker_llm_benchmark.yml

#2571 lxning closed 3 days ago
0
[lora] Fix predict adapter missing error code

#2570 xyang16 closed 3 days ago
0
[serving] Improve logging for exec shell command

#2569 xyang16 opened 5 days ago
1
[lora] Add adapter OOM unit tests

#2568 xyang16 closed 4 days ago
0
Support Sagemaker async endpoint deployment.

#2567 yinsong1986 opened 5 days ago
0
[docker] Update torch to 2.5.1 in docker

#2566 xyang16 closed 3 days ago
0
[sm][docker] use the correct verified cuda version in docker file

#2565 siddvenk closed 6 days ago
0
[python] Update output default error message

#2564 xyang16 closed 6 days ago
0
[lora] Add tests in lora integration test

#2563 xyang16 closed 5 days ago
0
[lmi][docs] update lmi documentation for v12 containers (#2560)

#2562 siddvenk closed 6 days ago
0
[lmi][python] remove quantization enum and rely on engine validation/…

#2561 siddvenk closed 6 days ago
0
[lmi][docs] update lmi documentation for v12 containers

#2560 siddvenk closed 6 days ago
0
neo shard script: remove `del engine` as engine doesn't exist any more

#2559 HappyAmazonian closed 1 week ago
0
[fix][ci] specify guaranteed_no_evict batch_scheduler_policy to get t…

#2558 siddvenk closed 1 week ago
0
[docker][lmi] update back to lmi nightly wheel

#2557 siddvenk closed 1 week ago
0
update neo sharding script to use load_model_for_sharding

#2556 HappyAmazonian closed 1 week ago
0
[docker] Update DJL pytorch to 2.5.1

#2555 xyang16 closed 1 week ago
0
[lora] Add lora configs and validation

#2554 xyang16 closed 1 week ago
0
[trt][docker] pin trt version to release version, not nightly

#2553 siddvenk closed 1 week ago
0
add Lora config to arg list in Neo sharding script& its integ test change

#2552 HappyAmazonian closed 1 week ago
0
[docker] fix cuda version label for lmi container

#2551 siddvenk closed 1 week ago
0