Ecosyste.ms: Issues

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

GitHub / intel-analytics/ipex-llm issues and pull requests

#12431 - support Llama2-7B / Llama3-8B for NPU C++

Pull Request - State: closed - Opened by rnwang04 1 day ago

#12430 - New convert support for C++ NPU

Pull Request - State: closed - Opened by rnwang04 1 day ago

#12429 - Update english prompt to 34k in vllm_online_benchmark.py

Pull Request - State: closed - Opened by liu-shaojun 1 day ago

#12428 - Error loading for file torch\lib\backend_with_compiler.dll

Issue - State: closed - Opened by LiangtaoJin 1 day ago - 1 comment

#12427 - nf4 still unsupported?

Issue - State: open - Opened by epage480 2 days ago - 1 comment

#12426 - Disable XMX

Issue - State: open - Opened by NikosDi 2 days ago

#12425 - small fix

Pull Request - State: closed - Opened by rnwang04 2 days ago

#12424 - Upgrade dependency for Windows LNL/ARL support

Pull Request - State: closed - Opened by Oscilloscope98 2 days ago

#12423 - add optimization to openjourney

Pull Request - State: closed - Opened by JinheTang 2 days ago

#12422 - Add release support for option `xpu_arc`

Pull Request - State: open - Opened by Oscilloscope98 3 days ago

#12421 - update batch kernel condition

Pull Request - State: closed - Opened by MeouSker77 3 days ago

#12418 - add Stable diffusion examples

Pull Request - State: closed - Opened by JinheTang 3 days ago

#12417 - Initial NPU C++ Example

Pull Request - State: closed - Opened by rnwang04 3 days ago

#12416 - Fix speech_paraformer issue with unexpected changes

Pull Request - State: closed - Opened by sgwhat 4 days ago - 2 comments

#12415 - Add multimodal benchmark

Pull Request - State: closed - Opened by hzjane 5 days ago

#12414 - Update benchmark_vllm_throughput.py

Pull Request - State: closed - Opened by gc-fu 5 days ago

#12413 - docs: add Japanese README

Pull Request - State: open - Opened by eltociear 6 days ago

#12412 - 'AutoModel' object has no attribute 'config' when using Speech_Paraformer-Large on NPU

Issue - State: open - Opened by fanyhchn 8 days ago - 1 comment
Labels: user issue

#12411 - Update Ollama with IPEX-LLM to a newer version

Issue - State: open - Opened by NikosDi 8 days ago - 1 comment
Labels: user issue

#12410 - [NPU] GW prefill merge qkv

Pull Request - State: open - Opened by cyita 8 days ago

#12408 - update batch kernel condition

Pull Request - State: closed - Opened by MeouSker77 8 days ago

#12407 - fix again

Pull Request - State: closed - Opened by rnwang04 9 days ago

#12406 - fix workflow again

Pull Request - State: closed - Opened by rnwang04 9 days ago

#12405 - Tiny doc fix

Pull Request - State: closed - Opened by Oscilloscope98 9 days ago - 1 comment

#12404 - Fix npu pipeline release workflow

Pull Request - State: closed - Opened by rnwang04 9 days ago

#12403 - Path of models using Ollama with IPEX-LLM (Windows)

Issue - State: closed - Opened by NikosDi 9 days ago - 4 comments

#12402 - [NPU] dump prefill IR for further C++ solution

Pull Request - State: closed - Opened by rnwang04 9 days ago - 1 comment

#12401 - Support performance mode of GLM4 model

Pull Request - State: closed - Opened by Oscilloscope98 9 days ago

#12400 - [NPU] change attention_mask to fp16

Pull Request - State: closed - Opened by plusbang 9 days ago

#12399 - Update readme & doc for the vllm upgrade to v0.6.2

Pull Request - State: closed - Opened by ATMxsp01 10 days ago

#12398 - Add padding_token=eos_token for GPU trl QLora example

Pull Request - State: closed - Opened by qiyuangong 10 days ago

#12397 - [NPU] attn_mask qwen2 small fix

Pull Request - State: closed - Opened by cyita 10 days ago

#12396 - use new q4_0 batch kernel

Pull Request - State: closed - Opened by MeouSker77 10 days ago

#12395 - [NPU] Qwen prefill attn_mask type hotfix

Pull Request - State: closed - Opened by cyita 10 days ago

#12394 - [NPU] Qwen prefill attn_mask type to fp16

Pull Request - State: closed - Opened by cyita 10 days ago

#12393 - Add initial support for modeling_xlm encoder on NPU

Pull Request - State: closed - Opened by sgwhat 10 days ago

#12392 - update vllm-docker-quick-start for vllm0.6.2

Pull Request - State: open - Opened by ACupofAir 10 days ago

#12391 - Llama-3.2 11B Vision not working with latest IPEX-LLM (vLLM version 0.6.2)

Issue - State: open - Opened by HumerousGorgon 10 days ago - 3 comments
Labels: user issue

#12390 - Fix the problem of vllm 0.6.2

Pull Request - State: open - Opened by gc-fu 11 days ago

#12389 - minor fix inference-cpp image

Pull Request - State: closed - Opened by liu-shaojun 11 days ago

#12388 - Update LangChain examples to use upstream

Pull Request - State: open - Opened by JinBridger 11 days ago

#12387 - Update llama-cpp docker usage

Pull Request - State: closed - Opened by hzjane 11 days ago

#12386 - changed inference-cpp/Dockerfile

Pull Request - State: closed - Opened by ATMxsp01 11 days ago

#12385 - assert error use ipex pytorch

Issue - State: closed - Opened by piDack 11 days ago - 4 comments
Labels: user issue

#12384 - Fix llava with multi-image inputs

Pull Request - State: closed - Opened by Oscilloscope98 11 days ago

#12383 - [NPU] Update qwen2 compile config

Pull Request - State: closed - Opened by rnwang04 12 days ago

#12382 - Decouple the openwebui and the ollama. in inference-cpp-xpu dockerfile

Pull Request - State: closed - Opened by ACupofAir 12 days ago - 4 comments

#12381 - Release with GitHub runner

Pull Request - State: open - Opened by SANKHA1 12 days ago

#12380 - Vulnerability issue CVE-2024-31583 and CVE-2024-31580 on torch<2.2.0

Issue - State: open - Opened by Johere 12 days ago - 4 comments
Labels: user issue

#12379 - Docker - llama.cpp scripts / init-llama-cpp

Issue - State: closed - Opened by easyfab 12 days ago - 2 comments
Labels: user issue

#12378 - Add `fused_mlp` to glm4v models

Pull Request - State: closed - Opened by Oscilloscope98 12 days ago

#12377 - Update oneccl-binding.patch

Pull Request - State: closed - Opened by liu-shaojun 12 days ago

#12376 - performance problem about internvl image embedding using ggml.dll

Issue - State: open - Opened by cjsdurj 13 days ago - 1 comment
Labels: user issue

#12375 - Support vpm and resampler module of minicpm-v on NPU

Pull Request - State: closed - Opened by plusbang 13 days ago

#12374 - Several GPU models behave erratically compared to CPU execution

Issue - State: open - Opened by pepijndevos 13 days ago - 2 comments
Labels: user issue

#12373 - using both iGPU and CPU together

Issue - State: open - Opened by fanlessfan 13 days ago - 6 comments
Labels: user issue

#12372 - Container cannot see Arc GPU

Issue - State: open - Opened by robertvazan 14 days ago - 12 comments
Labels: user issue

#12370 - update to ollama 0.4.0

Issue - State: open - Opened by Matthww 15 days ago - 8 comments
Labels: user issue

#12369 - optimize glm4v vision attention

Pull Request - State: closed - Opened by MeouSker77 15 days ago

#12368 - Fix trl version and padding in trl qlora example

Pull Request - State: closed - Opened by qiyuangong 15 days ago

#12367 - Update fastchat demo script

Pull Request - State: closed - Opened by liu-shaojun 15 days ago

#12366 - fix ipex 2.3 bug

Pull Request - State: closed - Opened by MeouSker77 16 days ago - 1 comment

#12365 - update linux installation doc

Pull Request - State: closed - Opened by qiuxin2012 16 days ago

#12364 - ipex-llm-cpp-xpu container

Issue - State: open - Opened by user7z 16 days ago - 3 comments
Labels: user issue

#12363 - cant run ollama in docker container with iGPU in linux

Issue - State: open - Opened by user7z 16 days ago - 8 comments
Labels: user issue

#12362 - Small fix to all-in-one benchmark

Pull Request - State: closed - Opened by Oscilloscope98 16 days ago

#12361 - [NPU L0] Support llama3.2 in L0 pipeline

Pull Request - State: closed - Opened by plusbang 16 days ago

#12360 - Add fused mlp optimizations to glm4 models

Pull Request - State: closed - Opened by Oscilloscope98 16 days ago

#12359 - small improvement

Pull Request - State: closed - Opened by MeouSker77 16 days ago

#12358 - Add troubleshootings for ollama and llama.cpp

Pull Request - State: closed - Opened by JinheTang 16 days ago

#12357 - Ollama & llamacpp troubleshooting

Pull Request - State: closed - Opened by JinheTang 16 days ago

#12356 - Could not use SFT Trainer in qlora_finetuning.py

Issue - State: open - Opened by shungyantham 16 days ago - 11 comments
Labels: user issue

#12355 - [NPU] acclib llama3.2 support groupwise

Pull Request - State: closed - Opened by cyita 17 days ago

#12354 - Update Readme for FastChat docker demo

Pull Request - State: closed - Opened by ATMxsp01 17 days ago

#12353 - Update install_linux_gpu.md, add version for Iris.

Pull Request - State: closed - Opened by qiuxin2012 17 days ago

#12352 - add minicpm-v models to `transformers_int4_npu_win` api

Pull Request - State: closed - Opened by JinheTang 17 days ago

#12351 - Small optimization to glm4 models

Pull Request - State: closed - Opened by Oscilloscope98 17 days ago

#12350 - fix three NPU benchmark issues

Pull Request - State: closed - Opened by rnwang04 17 days ago - 1 comment

#12349 - Add MiniCPM-V-2_6 to arc perf test

Pull Request - State: closed - Opened by JinBridger 17 days ago

#12348 - Ollama run embedding module mxbai-embed-large failed.

Issue - State: closed - Opened by feiyu11859661 17 days ago - 3 comments
Labels: user issue

#12347 - llama 3.1/3.2 support compresskv

Pull Request - State: closed - Opened by cyita 17 days ago - 2 comments

#12346 - optimize glm4v's vision part

Pull Request - State: closed - Opened by MeouSker77 17 days ago - 1 comment

#12345 - Add basic glm4v support

Pull Request - State: closed - Opened by MeouSker77 17 days ago - 1 comment

#12344 - [NPU] Hot fix of load_low_bit

Pull Request - State: closed - Opened by plusbang 18 days ago

#12342 - [NPU test] change lm as input and set weight at first

Pull Request - State: open - Opened by rnwang04 18 days ago

#12341 - Add dummy model in iGPU perf

Pull Request - State: closed - Opened by JinBridger 18 days ago

#12340 - Update Dockerfile

Pull Request - State: closed - Opened by liu-shaojun 18 days ago

#12339 - [NPU] Add Optimized Support for Llama3.2-1B/3B on NPU

Pull Request - State: closed - Opened by sgwhat 18 days ago - 1 comment

#12338 - Updates for vllm 0.6.2

Pull Request - State: closed - Opened by gc-fu 18 days ago - 2 comments

#12337 - [NPU] Support Baichuan groupwise & gw code refactor

Pull Request - State: closed - Opened by cyita 18 days ago

#12336 - fix chatglm2 cpu ut

Pull Request - State: closed - Opened by leonardozcm 18 days ago - 1 comment

#12333 - Small fix to LNL performance tests

Pull Request - State: closed - Opened by Oscilloscope98 19 days ago

#12332 - Limit trl version in example

Pull Request - State: closed - Opened by JinBridger 19 days ago