Heyang Sun issues

Results 14 issues of


Heyang Sun

Automation API 'io.dropwizard.jersey.errors.LoggingExceptionMapper: Error handling a request'

Hi guys, sorry to bother. I do really need a help when I send requests. Using curl or python requests lib to send GET or POST to keywhiz server, I...

Where can I find the automation APIs documents?

Hi guys, sorry to bother. Where can I find the automation API docs, about the interface explanations and use cases? I'd like to develop with URL requests. Thanks a lot.

[PPML] Graphene runtime env for python

## Description Turn graphene SGX init from using fixed argvs to using runtime envs. ### Why the change? Design a safer process of kubernetes deployment, in order to make up...

[PPML] Gramine MREnclave Enhancement

## Description Upgrade gramine SGX enclave to MREnclave, which is signed with hash values, and can be registered and attested by AS. ### 1. Why the change? Eliminate the leakage...

[PPML] run k8s examples with volcano and spark-operator

## Description Besides submit as spark job, BigDL k8s examples can also run as SparkApplication, which is a custom k8s resource. It is supported by custom controller spark-operator and scheduler...

Speculative Starcoder on CPU

## Description support and example of Startcode with speculative decoding on CPU ### 1. Why the change? as abvoe ### 2. User API changes no ### 3. Summary of the...

Baichuan2-13B with bigdl-bf16 does not apply greedy_search when calling model.generate

This is a **bigdl-bf16** model, where `model_path` is to a Baichuan2-13B-Chat: ```python # load model = AutoModelForCausalLM.from_pretrained(model_path, optimize_model=True, torch_dtype=torch.bfloat16, load_in_low_bit="bf16", trust_remote_code=True, use_cache=True) # inference original_output = model.generate(input_ids=input_ids, use_cache=False, max_new_tokens=args.n_predict, do_sample=False)...

Heyang Sun