intel llm-on-ray issues

intel / llm-on-ray

Pretrain, finetune and serve LLMs on Intel platforms with Ray

Apache License 2.0

103 stars 30 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

[Refactor] Remove dataset/tokenizer/model packaging under common, make pretrain/finetune scripts without common dependency.

#233 harborn closed 5 months ago
0
[Inference] Enable vllm on HPU

#232 KepingYan closed 5 months ago
0
Integrate vllm and inference engine (neural speed)

#231 jiafuzha closed 4 months ago
2
[CI] Change miniconda to miniforge

#230 yutianchen666 closed 5 months ago
0
Migrate CI to miniforge instead of miniconda

#229 xwu99 closed 5 months ago
0
Build docker files for both CI and User

#228 xwu99 closed 5 months ago
0
[Finetune] Resolve the exception caused by missing validation data and the missing gaudi_config parameter in GaudiTrainer.

#227 minmingzhu closed 5 months ago
2
Fix max_new_tokens for HPU predictcor

#226 carsonwang closed 6 months ago
0
[Inference] Add validated models for Gaudi

#225 Deegue closed 4 months ago
5
Revise README.md in examples directory

#224 xwu99 opened 6 months ago
0
expected scalar type BFloat16 but found Float

#223 darmenliu opened 6 months ago
1
Calculate correct input length for every prompt in a single batch

#222 kira-lin opened 6 months ago
0
Add serve command line options to list all supported model-ids

#221 yutianchen666 closed 5 months ago
2
[Inference] Remove simple mode and use OpenAI API

#220 Deegue closed 6 months ago
0
Build docker files for both CI and User

#219 yutianchen666 closed 4 months ago
1
Output some debug info in CI when Internal Server Error

#218 xwu99 opened 6 months ago
0
Define simple_protocol.py and define pydantic SimpleRequest and SimpleModelResponse classes to encapsulate current json format

#217 xwu99 opened 6 months ago
0
Docker files for both CI and User

#216 xwu99 closed 4 months ago
0
Fix StoppingCriteriaSub parameters to be compatible with latest Transformers

#215 kira-lin closed 6 months ago
0
[Inference] Add autoscaling config

#214 KepingYan closed 5 months ago
0
[Inference] Fix openai response

#213 KepingYan closed 6 months ago
1
Update VLLM installation script and documentation

#212 xwu99 closed 6 months ago
0
Consolidate deepspeed workers for DeepSpeedPredictor and HPUPredictor

#211 xwu99 closed 6 months ago
0
[CI] Fix proxy

#210 KepingYan closed 6 months ago
0
Refactor non-streaming generate

#209 xwu99 closed 6 months ago
0
[CI] Add llama2-70b inference workflow

#208 Deegue closed 6 months ago
1
Add support for HPU quantization and torch_compile

#207 kira-lin closed 6 months ago
0
fix ci ipex version

#206 minmingzhu closed 6 months ago
0
Integrate web UI with chat template

#205 minmingzhu opened 6 months ago
0
[Finetune] replace fine-tuning DefaultTrainer with transformers.Trainer

#204 harborn closed 6 months ago
1
Bump pydantic from 1.10.11 to 1.10.13 in /llm_on_ray/pretrain

#203 dependabot[bot] closed 6 months ago
0
Migrate OpenAI API to 1.0

#202 xwu99 closed 6 months ago
1
Add config files for Llama3 on HPU

#201 kira-lin closed 6 months ago
0
Fix bug: deal with string in config file

#200 kira-lin closed 7 months ago
0
[Inference ] Integrate chat template in llm-on-ray

#199 minmingzhu closed 6 months ago
2
Delete bigdl related files

#198 yutianchen666 closed 7 months ago
0
Issue about using ipex on cpu

#197 KepingYan opened 7 months ago
0
[Habana] update habana docker image

#196 harborn closed 7 months ago
1
Add benchmark run script, figure visualization script

#195 KepingYan closed 5 months ago
1
Bump pypdf from 3.12.0 to 3.17.0 in /application

#194 dependabot[bot] closed 7 months ago
0
Bump streamlit from 1.24.0 to 1.30.0 in /application

#193 dependabot[bot] closed 7 months ago
0
Bump langchain from 0.0.228 to 0.1.0 in /application

#192 dependabot[bot] closed 7 months ago
0
Added the Application:codegen based on the LLM-on-Ray Service

#191 yao531441 closed 6 months ago
4
[Inference] integrate deepseek-coder-33b-instruct.

#190 yao531441 closed 7 months ago
2
[Bigdl] Change all "bigdl" to "ipexllm"

#189 yutianchen666 closed 7 months ago
2
Added the Application based on the LLM-on-Ray Service

#188 tianyil1 closed 7 months ago
4
[BigDL] Update bigdl-llm to ipex-llm

#187 yutianchen666 closed 7 months ago
2
Fix UI bugs and upgrade to ray 2.10

#186 KepingYan closed 7 months ago
0
[CI] Add Gaudi2 inference workflow

#185 Deegue closed 6 months ago
1
Move parameter ignore_eos to benchmark script

#184 KepingYan closed 7 months ago
1

Previous Next