Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / microsoft/DeepSpeed-MII issues and pull requests
#546 - How to use data parallelism in multi gpus inference
Issue -
State: open - Opened by hhf-hu 4 days ago
#545 - Issue: Multi-node and Multi-GPU Inference Problems with DeepSpeed MII
Issue -
State: open - Opened by lcnmzz00 6 days ago
#544 - Please clarify structured output support
Issue -
State: open - Opened by MRYingLEE 7 days ago
#543 - Bug: Removal of mii.pydantic_v1 broke entrypoint scripts
Issue -
State: open - Opened by KMouratidis 15 days ago
- 3 comments
#542 - Update transformers
Pull Request -
State: open - Opened by loadams 18 days ago
#541 - Updating transformers issue with bloom models
Issue -
State: open - Opened by loadams 25 days ago
#540 - Updating transformers issue with zero-shot-image-classification
Issue -
State: open - Opened by loadams 25 days ago
#539 - Update version.txt
Pull Request -
State: closed - Opened by loadams 27 days ago
#538 - Update clang-format version to match DeepSpeed
Pull Request -
State: closed - Opened by loadams 27 days ago
#537 - Update path triggers that were incorrect before
Pull Request -
State: closed - Opened by loadams 27 days ago
#536 - Non-persistent example fails with KeyError
Issue -
State: closed - Opened by jjaymick001 28 days ago
- 1 comment
#535 - Update CODEOWNERS
Pull Request -
State: closed - Opened by loadams 28 days ago
#534 - Update labels to acquire new runners
Pull Request -
State: closed - Opened by loadams 28 days ago
#533 - Update docker container version
Pull Request -
State: closed - Opened by loadams 29 days ago
#532 - Logits Processors
Issue -
State: open - Opened by psitronic about 1 month ago
#531 - need help understanding profiler in deespeed mio
Issue -
State: open - Opened by krishnanpooja about 2 months ago
#530 - Deepspeed mii library issues
Issue -
State: closed - Opened by gayatripadmani about 2 months ago
- 2 comments
#529 - DeepSpeed with Phi-3-mini-128K-instruct does not generate `<|endoftext|>` token
Issue -
State: open - Opened by shubhanshu786 2 months ago
- 1 comment
#528 - Repeated token generation with Phi-3-mini for longer context
Issue -
State: open - Opened by shubhanshu786 2 months ago
#527 - LoRA Support
Issue -
State: open - Opened by bagelbig 2 months ago
#526 - deepspeed MoE all_to_all communication
Issue -
State: open - Opened by miaomiaoma0703 2 months ago
#525 - multi model deployment
Issue -
State: open - Opened by whcjb 2 months ago
- 1 comment
#524 - Fix missing pydantic updates in legacy mii code
Pull Request -
State: closed - Opened by loadams 3 months ago
#523 - Question About Offloading and Recomputation
Issue -
State: open - Opened by lxnlxnlxnlxnlxn 3 months ago
#522 - Configuration setting to pass parameters to tokenizer while encoding and decoding
Issue -
State: open - Opened by krishnanpooja 3 months ago
#521 - OpenAI server fails
Issue -
State: open - Opened by nivibilla 3 months ago
- 1 comment
#520 - Update version.txt after 0.3.0 release
Pull Request -
State: closed - Opened by loadams 3 months ago
#519 - Update supported model list
Pull Request -
State: closed - Opened by tohtana 3 months ago
#518 - By default does deepspeed mii use bf16 dtype or fp16?
Issue -
State: open - Opened by krishnanpooja 3 months ago
#517 - Confirm PyDantic v2 update passes DS tests
Pull Request -
State: closed - Opened by loadams 3 months ago
#516 - FileExistsError: [Errno 17] File exists: '/tmp/mii_cache' ` on generate function call
Issue -
State: open - Opened by krishnanpooja 4 months ago
#515 - Fix scheduling for non-persistent pipeline
Pull Request -
State: closed - Opened by tohtana 4 months ago
#514 - Can't use Llama 3.1 with MII, ImportError: cannot import name 'Conversation' from 'transformers'
Issue -
State: closed - Opened by chuyuanli 4 months ago
- 1 comment
#513 - non-persistent example doesn't work on Mixtral-8*7B-v0.1
Issue -
State: open - Opened by tang-t21 4 months ago
#512 - Support latest changes in transformers
Pull Request -
State: open - Opened by loadams 4 months ago
#511 - Update version.txt
Pull Request -
State: closed - Opened by loadams 4 months ago
#510 - Pin to use a specific version of transformers
Pull Request -
State: closed - Opened by loadams 4 months ago
#509 - Test adding torchvision to fix CI failures
Pull Request -
State: closed - Opened by loadams 4 months ago
#508 - Update workflow task to use Ubuntu 22.04
Pull Request -
State: closed - Opened by loadams 4 months ago
#507 - Update MII to switch from modelid to id
Pull Request -
State: closed - Opened by loadams 4 months ago
#506 - non-persistent simple example does not work
Issue -
State: open - Opened by mohbay 4 months ago
- 5 comments
#505 - Dummy data loading?
Issue -
State: open - Opened by guqiqi 5 months ago
#504 - Client cannot find deployment error
Issue -
State: open - Opened by heiseon 5 months ago
#503 - CUDA device rank in mii.pipeline
Issue -
State: open - Opened by RealPolitiX 5 months ago
#502 - Import Error, not compatible with transformer package
Issue -
State: closed - Opened by tang-t21 5 months ago
- 4 comments
#501 - deepseed-mii支持多节点推理么
Issue -
State: closed - Opened by JKYtydt 5 months ago
- 2 comments
#500 - Run pydantic 2 tests with updated DeepSpeed branch
Pull Request -
State: closed - Opened by loadams 5 months ago
#499 - Test
Pull Request -
State: closed - Opened by trapp3rhat 5 months ago
#498 - [QUERY] Expert Parallelism Supported?
Issue -
State: open - Opened by Shamauk 5 months ago
#497 - Attempting to flush sequence N which does not exist
Issue -
State: open - Opened by aagontuk 5 months ago
#496 - Compute perplexity
Issue -
State: open - Opened by Sh1gechan 5 months ago
#495 - Configure server log level
Issue -
State: open - Opened by sedletsky-f5 5 months ago
- 2 comments
#494 - few questions regarding the implementation of streaming and batching
Issue -
State: open - Opened by KimMinSang96 6 months ago
#493 - Add explanations of MII code into comments
Pull Request -
State: closed - Opened by mrwyattii 6 months ago
#492 - Remove Conversation from MII as it was deprecated and removed from transformers.
Pull Request -
State: closed - Opened by loadams 6 months ago
- 1 comment
#491 - Always Flush UIDs after Exceptions
Pull Request -
State: closed - Opened by weiqisun 6 months ago
#490 - Always Flush UIDs after `GeneratorReply`
Pull Request -
State: closed - Opened by weiqisun 6 months ago
- 1 comment
#489 - [BUG] MII Backend Hangs After 9999 Exceptions in `MIIAsyncPipeline.put_request`
Issue -
State: closed - Opened by weiqisun 6 months ago
- 2 comments
#488 - support stream
Issue -
State: open - Opened by ZZhangxian 6 months ago
#487 - support Qwen1.5
Issue -
State: open - Opened by ZZhangxian 6 months ago
#486 - support Qwen
Issue -
State: closed - Opened by ZZhangxian 6 months ago
#485 - Some fixes to make openai entrypoint work out of the box
Pull Request -
State: closed - Opened by svaruag 6 months ago
#484 - Reuse KV cache of prefixes
Pull Request -
State: open - Opened by tohtana 6 months ago
#483 - Support LLava next stronger
Issue -
State: open - Opened by thesby 6 months ago
#482 - How can I use the same prompt to produce the same text output as vllm
Issue -
State: open - Opened by Greatpanc 6 months ago
#481 - Tf32 support
Issue -
State: open - Opened by Chasapas 6 months ago
#480 - Enable streaming option in the OpenAI API server
Pull Request -
State: closed - Opened by adk9 6 months ago
#479 - DeepSpeed-MII 能加载量化的int4或者int8的模型吗?
Issue -
State: open - Opened by wangyongpenga 6 months ago
#478 - Fix deprecation warning on escaped characters
Pull Request -
State: closed - Opened by loadams 6 months ago
#477 - Does deepspeed-mii support prefix_allowed_tokens_fn?
Issue -
State: open - Opened by zcakzhuu 7 months ago
#476 - Update mistral tests to fully open source version.
Pull Request -
State: closed - Opened by loadams 7 months ago
#475 - [REQUEST] LLAMA-3 support
Issue -
State: open - Opened by MRYingLEE 7 months ago
#474 - [REQUEST] Mixtral-8x22B support
Issue -
State: open - Opened by y-live-koba 7 months ago
#473 - Allow model to generate added tokens - fix generation issue in Llama3 models
Pull Request -
State: closed - Opened by weiqisun 7 months ago
- 9 comments
#472 - Cannot run Yi-34B-Chat => ValueError: Unsupported q_ratio: 7
Issue -
State: open - Opened by joeking11829 7 months ago
- 3 comments
#471 - BUG in run_batch_processing
Issue -
State: open - Opened by zhihui96 7 months ago
#470 - fix max_ragged_sequence_count check in _schedule_prompts
Pull Request -
State: closed - Opened by dc3671 7 months ago
- 1 comment
#469 - ValueError: Unsupported model type phi3
Issue -
State: open - Opened by abpani 7 months ago
- 1 comment
#468 - error when using Qwen1.5-32B
Issue -
State: open - Opened by puppet101 7 months ago
- 1 comment
#467 - Performance with vllm
Issue -
State: open - Opened by littletomatodonkey 7 months ago
- 1 comment
#466 - [Problem]errno: 98 - Address already in use
Issue -
State: closed - Opened by littletomatodonkey 7 months ago
#465 - Only running one replica even though setting many replicas
Issue -
State: open - Opened by thesby 7 months ago
- 1 comment
#464 - RuntimeError: The server socket has failed to listen on any local network address
Issue -
State: open - Opened by thesby 7 months ago
- 2 comments
#463 - [FEATURE] Access to logits and final hidden layer
Issue -
State: open - Opened by lshamis 7 months ago
- 1 comment
#462 - How is the prompt segmentation specifically implemented for Dynamic SplitFuse? Is there any code implement or code snippet ?
Issue -
State: open - Opened by wenyangchou 7 months ago
#461 - Update create a PR workflow to latest version withh node js 20 fixes
Pull Request -
State: closed - Opened by loadams 7 months ago
#460 - How do I launch the api on a graphics card other than cuda: 0
Issue -
State: open - Opened by Stark-zheng 8 months ago
- 1 comment
#459 - Is openai compatible server still working?
Issue -
State: closed - Opened by RobinQu 8 months ago
- 1 comment
#458 - how can I use deepspeed to split the model to submit GPU?
Issue -
State: open - Opened by WanBenLe 8 months ago
#457 - [FEATURE REQUEST] Add Support for Qwen1.5-MoE Architecture in DeepSpeed-MII
Issue -
State: open - Opened by freQuensy23-coder 8 months ago
- 1 comment
#452 - inference_core_ops.so: undefined symbol: _Z19cuda_wf6af16_linearRN2at6TensorES1_S1_S1_S1_S1_iiii
Issue -
State: open - Opened by Andronixs 8 months ago
- 6 comments
#450 - How can i use this library with langchain or llama_index?
Issue -
State: open - Opened by risedangel 8 months ago
- 2 comments
#449 - Block when Call client inference in multiprocessing.Process
Issue -
State: open - Opened by zhaotyer 8 months ago
- 3 comments
#445 - Add Kubernetes health check route to REST server
Pull Request -
State: closed - Opened by richiejp 8 months ago
#444 - server crashed for some reason, unable to proceed
Issue -
State: open - Opened by Archmilio 8 months ago
- 1 comment
#443 - [BUG] Issue serving Mixtral 8x7B on H100
Issue -
State: open - Opened by Rogerwyf 8 months ago
- 9 comments
#442 - qwen1.5 model Support?
Issue -
State: open - Opened by musexiaoluo 9 months ago
- 3 comments
#441 - On M3 Pro Macbook having issues with installation
Issue -
State: closed - Opened by HariKunapareddy 9 months ago
- 2 comments
#440 - [NEED HELP] Quantization inference
Issue -
State: open - Opened by freQuensy23-coder 9 months ago
- 2 comments
#439 - Quantization inference
Issue -
State: open - Opened by freQuensy23-coder 9 months ago
- 1 comment