microsoft/T-MAC issues and pull requests

#46 - Merge llama.cpp b69a480

Pull Request - State: open - Opened by kaleid-liner 4 days ago

#45 - T-MAC 1.0.0 Release Plan

Issue - State: open - Opened by kaleid-liner 5 days ago
Labels: enhancement

#44 - How to test kernel performance using your code?

Issue - State: open - Opened by orange-juice1 6 days ago - 4 comments
Labels: question

#43 - compile llama.cpp failed

Issue - State: closed - Opened by qw1319 8 days ago - 2 comments

#42 - Compile TVM failed

Issue - State: closed - Opened by velonica0 9 days ago - 4 comments
Labels: bug

#41 - Whether the T-MAC supports the RISC-V CPU？

Issue - State: open - Opened by velonica0 11 days ago - 1 comment
Labels: enhancement

#40 - Slow performance compared to llama.cpp origin

Issue - State: open - Opened by idreamerhx 13 days ago - 7 comments
Labels: question

#39 - performance on mobile phone such as MTK D9000/D8300 or Qualcomm 8Gen3

Issue - State: open - Opened by yuimo 15 days ago - 2 comments
Labels: duplicate

#38 - [Question]Whether T-MAC supports mixed-precision LLM?

Issue - State: open - Opened by AndreaChiChengdu 16 days ago - 1 comment

#37 - where is t-mac-envs.sh

Issue - State: closed - Opened by idreamerhx 17 days ago - 4 comments
Labels: bug, duplicate

#36 - [Fix] Try to fix ubuntu installation (#26)

Pull Request - State: closed - Opened by kaleid-liner 20 days ago - 1 comment

#34 - Question about "Bit-serial linear transformation" in paper

Issue - State: closed - Opened by zjnyly 21 days ago - 1 comment

#33 - How to get more detail information

Issue - State: closed - Opened by yoghur 21 days ago - 4 comments
Labels: question

#32 - 8gen3 T-MAC cpu performance issue

Issue - State: open - Opened by AndreaChiChengdu 21 days ago - 9 comments
Labels: enhancement, good first issue

#31 - llama-2-7b 4bit convert fail issue(2bit is ok)

Issue - State: closed - Opened by AndreaChiChengdu 22 days ago - 3 comments

#30 - How to Fully Utilize the Optimized Performance of T-MAC ?

Issue - State: open - Opened by ma-hang 22 days ago - 2 comments
Labels: question

#29 - Add Android cross-compilation support (feat #12, #18)

Pull Request - State: closed - Opened by kaleid-liner 25 days ago

#28 - OpenAI compatible chat completions endpoint

Issue - State: open - Opened by maxim-saplin 26 days ago - 9 comments

#27 - 【Qwen】Could you please update 3rd/llama.cpp to support Qwen1.5 or Qwen2 ?

Issue - State: open - Opened by tiger-of-shawn 28 days ago - 13 comments
Labels: duplicate

#26 - ubuntu installation problem on Google colab

Issue - State: open - Opened by amirhosein-darmani 30 days ago - 25 comments
Labels: bug

#25 - Cannot run compile.py on my Apple M1Max.

Issue - State: closed - Opened by begoss 30 days ago - 5 comments
Labels: bug

#24 - Any plans to merge the latest code of llama.cpp?

Issue - State: open - Opened by peytoncai 30 days ago - 3 comments

#23 - How to build ollama with t-mac support？

Issue - State: open - Opened by goukisun 30 days ago - 1 comment
Labels: help wanted

#22 - question about run_pipeline.py

Issue - State: closed - Opened by sunj0104 about 1 month ago - 5 comments

#21 - how to add new models and their kernels?

Issue - State: closed - Opened by jason-zou about 1 month ago - 1 comment

#20 - Thanks for the excellent work, what happens when let the CPU and GPU (or other) do the inference operations at the same time.

Issue - State: open - Opened by aoom about 1 month ago - 1 comment
Labels: enhancement

#19 - The program hangs when I run the command "pip install . -v"

Issue - State: closed - Opened by spxcds about 1 month ago - 1 comment

#18 - Document for cross-compile for low-end devices

Issue - State: closed - Opened by ljy6j13 about 1 month ago - 2 comments
Labels: documentation

#17 - Question about running run_pipeline.py

Issue - State: closed - Opened by qiuqiu10 about 1 month ago - 3 comments
Labels: question

#16 - chore: update run_pipeline.py

Pull Request - State: closed - Opened by eltociear about 1 month ago - 1 comment

#13 - 是否可以在llama.cpp中体验该项目的优化功能

Issue - State: closed - Opened by CsBoBoNice about 1 month ago - 1 comment

#10 - have any plan embeded in mlc llm?

Issue - State: open - Opened by lhwlhw90 about 1 month ago
Labels: enhancement

#9 - codegen Error in cross-compiling Android on Mac

Issue - State: closed - Opened by zk1998 about 2 months ago - 3 comments
Labels: bug

#8 - Cannot compile your llama.cpp with CUDA support on AGX Orin

Issue - State: closed - Opened by Zijie-Tian 3 months ago - 4 comments

#7 - E2E integration into llama.cpp

Pull Request - State: closed - Opened by kaleid-liner 5 months ago

#6 - Update README.md

Pull Request - State: closed - Opened by caoting-dotcom 5 months ago

#5 - Action required: migrate or opt-out of migration to GitHub inside Microsoft

Issue - State: closed - Opened by microsoft-github-policy-service[bot] 6 months ago - 7 comments

#4 - Create action codeql.yml

Pull Request - State: closed - Opened by kaleid-liner 6 months ago

#3 - Add Intel CPU AVX2 support

Pull Request - State: closed - Opened by kaleid-liner 6 months ago

#2 - Update README.md

Pull Request - State: closed - Opened by kaleid-liner 8 months ago

#1 - Initial commit

Pull Request - State: closed - Opened by kaleid-liner 8 months ago

GitHub / microsoft/T-MAC issues and pull requests