Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / ModelTC/lightllm issues and pull requests

#503 - add benchmark of prompt cache

Pull Request - State: closed - Opened by WANDY666 3 months ago

#502 - What team are the developers from?

Issue - State: closed - Opened by CSEEduanyu 3 months ago - 1 comment
Labels: bug

#501 - edit docs

Pull Request - State: closed - Opened by fubaosu 3 months ago

#500 - add readthedocs yaml

Pull Request - State: closed - Opened by shihaobai 3 months ago

#499 - fix push_metrics crash

Pull Request - State: closed - Opened by shihaobai 3 months ago

#498 - fix Mistral for 13B

Pull Request - State: closed - Opened by shihaobai 3 months ago

#497 - Add support for OpenGVLab/InternVL2-Llama3-76B

Pull Request - State: closed - Opened by flyinglandlord 3 months ago

#496 - ADD CN and EN docs

Pull Request - State: closed - Opened by fubaosu 3 months ago

#495 - update_readme_internvl

Pull Request - State: closed - Opened by SangChengC 3 months ago

#494 - delete debug info

Pull Request - State: closed - Opened by WANDY666 3 months ago

#492 - add __init__.py

Pull Request - State: closed - Opened by fubaosu 3 months ago

#491 - Suport reward model with tp

Pull Request - State: closed - Opened by fubaosu 3 months ago

#490 - torch, triton版本确认及显存占用分析

Issue - State: open - Opened by LittleYouEr 3 months ago - 8 comments

#489 - Suport reward model

Pull Request - State: closed - Opened by fubaosu 3 months ago

#488 - add internlm-reward model suport

Pull Request - State: closed - Opened by fubaosu 3 months ago

#487 - add internlm-reward model suport

Pull Request - State: closed - Opened by fubaosu 3 months ago

#486 - add internlm-reward model suport

Pull Request - State: closed - Opened by fubaosu 3 months ago

#485 - suport internlm-reward model

Pull Request - State: closed - Opened by fubaosu 3 months ago

#484 - support Internvl1.5 model

Pull Request - State: closed - Opened by SangChengC 3 months ago

#483 - Fix splitfuse qwen

Pull Request - State: closed - Opened by flyinglandlord 3 months ago

#482 - 请支持minicpmv2.5

Issue - State: open - Opened by LDLINGLINGLING 3 months ago - 3 comments
Labels: bug

#481 - support llama3.1 rope rotary

Pull Request - State: closed - Opened by hiworldwzj 3 months ago

#479 - question about fp8 version of context_flashattention_nopad.py

Issue - State: open - Opened by changyuanzhangchina 4 months ago - 2 comments
Labels: bug

#478 - Fix bug for multi release multimodal_resources

Pull Request - State: closed - Opened by hiworldwzj 4 months ago

#477 - fix prompt cache with input lenght =1

Pull Request - State: closed - Opened by shihaobai 4 months ago

#438 - fix log for mean_per_token_cost_time

Pull Request - State: closed - Opened by hiworldwzj 5 months ago

#417 - Add triton w8a8

Pull Request - State: closed - Opened by helloyongyang 5 months ago

#404 - 请问是否有计划支持MiniCPM-V-2

Issue - State: open - Opened by xiabo0816 7 months ago - 2 comments

#100 - 输出结果问题

Issue - State: open - Opened by listenyb about 1 year ago - 2 comments

#99 - Add `id` and `logprob` to `generate_stream`

Pull Request - State: closed - Opened by ChieloNewctle about 1 year ago - 1 comment

#98 - Add a cn doc about how to add a new model

Pull Request - State: closed - Opened by hiworldwzj about 1 year ago

#97 - support sending input_emds as input for TpPartBaseModel.forward

Pull Request - State: closed - Opened by lighten001 about 1 year ago - 1 comment

#96 - Internlm

Pull Request - State: closed - Opened by shihaobai about 1 year ago

#95 - [BUG] triton version confict

Issue - State: closed - Opened by fredbjer about 1 year ago - 4 comments
Labels: bug

#94 - Fix installer not copying all files

Pull Request - State: closed - Opened by singularity-s0 about 1 year ago - 1 comment

#93 - Support for NTK-aware Scaled RoPE from Environment Variables

Pull Request - State: closed - Opened by singularity-s0 about 1 year ago - 1 comment

#92 - Are there any plans to support interfaces in openai format？

Issue - State: closed - Opened by Zhang-star-master about 1 year ago - 2 comments
Labels: enhancement

#91 - fix bug for aborted req

Pull Request - State: closed - Opened by hiworldwzj about 1 year ago

#90 - [QUESTION] Is it expected to see an exception when running `benchmark_serving.py`

Issue - State: closed - Opened by UranusSeven about 1 year ago - 2 comments
Labels: bug

#89 - [BUG] AttributeError: 'NoneType' object has no attribute 'to_ir'

Issue - State: closed - Opened by ehartford about 1 year ago - 4 comments
Labels: bug

#88 - [BUG]llama2-70B 加载完成后，无法启动服务

Issue - State: closed - Opened by ChristineSeven about 1 year ago - 8 comments
Labels: bug

#87 - Update README.md to Add support For Baichuan13B

Pull Request - State: closed - Opened by hiworldwzj about 1 year ago

#86 - Refactor the code to make adding models easier.

Pull Request - State: closed - Opened by hiworldwzj about 1 year ago

#85 - Starcoder chatglm2

Pull Request - State: closed - Opened by shihaobai about 1 year ago

#84 - 是否有计划支持 lora？

Issue - State: open - Opened by Haskely about 1 year ago - 3 comments
Labels: enhancement

#83 - [BUG]No module named 'lightllm.models.chatglm2.triton_kernel

Issue - State: closed - Opened by glsoon about 1 year ago - 6 comments
Labels: bug

#82 - Support for NTK-aware Scaled RoPE

Pull Request - State: closed - Opened by singularity-s0 about 1 year ago - 4 comments

#81 - Support automatically calculate max_total_token_num

Pull Request - State: open - Opened by singularity-s0 about 1 year ago - 7 comments

#80 - Triton Error [CUDA]: invalid argument

Issue - State: closed - Opened by jemmyshin about 1 year ago - 4 comments
Labels: bug

#79 - lightllm vs vllm

Issue - State: closed - Opened by tonylin52 about 1 year ago - 6 comments

#77 - Update shield

Pull Request - State: closed - Opened by llehtahw about 1 year ago

#76 - Update about discord

Pull Request - State: closed - Opened by llehtahw about 1 year ago

#75 - 当我执行abort之后，请求是否会立马被终止？

Issue - State: closed - Opened by HuaYZhao about 1 year ago - 4 comments
Labels: bug

#74 - fix readme.md

Pull Request - State: closed - Opened by hiworldwzj about 1 year ago

#73 - Supporting GPT-NEO and GPT-NEOX

Issue - State: open - Opened by goodbai-nlp about 1 year ago
Labels: enhancement

#72 - Update issue templates

Pull Request - State: closed - Opened by llehtahw about 1 year ago

#71 - 输入参数问题

Issue - State: closed - Opened by UncleFB about 1 year ago - 13 comments

#70 - fix readme

Pull Request - State: closed - Opened by hiworldwzj about 1 year ago

#69 - fix readme

Pull Request - State: closed - Opened by hiworldwzj about 1 year ago

#68 - fix readme

Pull Request - State: closed - Opened by hiworldwzj about 1 year ago

#67 - Support Baichuan-7B

Pull Request - State: closed - Opened by hiworldwzj about 1 year ago

#66 - Whether to support single card multi-instance loading

Issue - State: open - Opened by dushulin about 1 year ago - 4 comments

#65 - Support OpenAI-Compatible APIs

Issue - State: closed - Opened by merrymercy over 1 year ago - 2 comments
Labels: enhancement

#64 - Cannot use NsightSystems to trace gpu usage

Issue - State: closed - Opened by leiwen83 over 1 year ago - 2 comments

#63 - Modify readme about container multiple GPUs usage

Pull Request - State: closed - Opened by llehtahw over 1 year ago

#62 - Auto convert without tokenizer.json to prevent performance downgrade?

Issue - State: open - Opened by leiwen83 over 1 year ago - 2 comments

#61 - ziya运行报错，求助

Issue - State: closed - Opened by njhouse365 over 1 year ago - 15 comments

#60 - fix Qwen-7b --tp 2 load weights bug

Pull Request - State: closed - Opened by hiworldwzj over 1 year ago

#59 - Update dockerfile and related readme

Pull Request - State: closed - Opened by llehtahw over 1 year ago

#58 - Refactoring the implementation of throughput analysis logs

Pull Request - State: closed - Opened by hiworldwzj over 1 year ago

#57 - RuntimeError("Distributed package doesn't have NCCL " "built in")

Issue - State: closed - Opened by shanekong over 1 year ago - 4 comments

#56 - why lightllm not suport ChatGLM-6b?

Issue - State: closed - Opened by cabbagetalk over 1 year ago - 1 comment

#55 - fix Qwen-7b start error

Pull Request - State: closed - Opened by hiworldwzj over 1 year ago

#54 - benchmark无法完整运行

Issue - State: closed - Opened by HuaYZhao over 1 year ago - 3 comments

#53 - update context_flashattention triton kernel to support V100

Pull Request - State: closed - Opened by hiworldwzj over 1 year ago

#52 - run error with baichuan-7B

Issue - State: closed - Opened by HalFTeen over 1 year ago - 7 comments

#51 - Add docker build action

Pull Request - State: closed - Opened by llehtahw over 1 year ago - 1 comment

#50 - fix bug for start up llama2

Pull Request - State: closed - Opened by hiworldwzj over 1 year ago

#49 - Report traceback from router init process

Pull Request - State: closed - Opened by llehtahw over 1 year ago

#48 - 计划什么时候支持baichuan-13b-chat ？

Issue - State: closed - Opened by Zhang-star-master over 1 year ago - 7 comments
Labels: bug

#47 - add support for chatglm and trust_remote_code

Pull Request - State: closed - Opened by shihaobai over 1 year ago

#46 - Support Qwen-7b

Pull Request - State: closed - Opened by hiworldwzj over 1 year ago - 1 comment

#45 - run error

Issue - State: closed - Opened by UncleFB over 1 year ago - 11 comments
Labels: bug

#44 - Run error

Issue - State: closed - Opened by lucasjinreal over 1 year ago - 14 comments
Labels: bug

#43 - Any docs for support other new models?

Issue - State: closed - Opened by lucasjinreal over 1 year ago - 1 comment
Labels: documentation

#42 - Fix garbled Chinese output

Pull Request - State: closed - Opened by llehtahw over 1 year ago

#41 - 关于多并发时，batch_size的调整

Issue - State: closed - Opened by zackdist over 1 year ago - 2 comments

#40 - Does lightllm support Qwen-7B deployment?

Issue - State: closed - Opened by songkq over 1 year ago - 14 comments
Labels: bug, enhancement

#39 - RuntimeError: CUDA: Error- invalid source

Issue - State: closed - Opened by ChristineSeven over 1 year ago - 14 comments

#38 - Add log to print average tokens throughput.

Pull Request - State: closed - Opened by shanshanpt over 1 year ago - 4 comments

#36 - Fix the encoding problem of Chinese

Pull Request - State: closed - Opened by shihaobai over 1 year ago

#35 - llama-7B一直卡在启动部分

Issue - State: closed - Opened by HalFTeen over 1 year ago - 24 comments

#34 - RuntimeError: Triton Error [CUDA]: invalid argument

Issue - State: closed - Opened by andy-yang-1 over 1 year ago - 5 comments

#33 - add support for starcoder

Pull Request - State: closed - Opened by shihaobai over 1 year ago

#32 - support int8kv cache in llama model

Pull Request - State: closed - Opened by hiworldwzj over 1 year ago