enable TL2 build on Windows (Clang/MSVC) + add Qwen2.5-32B kernel support#523
Open
vladimirmoushkov wants to merge 2 commits intomicrosoft:mainfrom
Open
enable TL2 build on Windows (Clang/MSVC) + add Qwen2.5-32B kernel support#523vladimirmoushkov wants to merge 2 commits intomicrosoft:mainfrom
vladimirmoushkov wants to merge 2 commits intomicrosoft:mainfrom
Conversation
- Set CMAKE_CXX_STANDARD=17 in root CMakeLists (required for <chrono>)
- Fix const correctness in ggml-bitnet-mad.cpp (Clang -Werror)
- Add windows-tl2-build-fixes.patch for llama.cpp submodule:
- Enable C++17 for GGML_BITNET_X86_TL2 builds
- Add explicit pointer casts in ggml.c TL2 path (C strict typing)
- Add missing #include <chrono> in common.cpp, log.cpp,
imatrix.cpp, perplexity.cpp
Tested: Clang 22.1.2 + MSVC BuildTools on Windows 11, Intel 12700K.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add Qwen2.5-32B-TL2 model to codegen_tl2.py ModelShapeDict with matrix dims: 5120x5120, 1024x5120, 27648x5120, 5120x27648 - Include pre-generated bitnet-lut-kernels.h and kernel_config.ini for Qwen2.5-32B (BM=256/128, BK=96, bm=32) Verified: 1.45-1.87 tok/s generation on Intel 12700K (AVX2, 16 threads) with 32.77B parameter TL2 model at 2.74 BPW. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
@vladimirmoushkov please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.
Contributor License AgreementContribution License AgreementThis Contribution License Agreement (“Agreement”) is agreed to by the party signing below (“You”),
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
The TL2 x86 kernel path does not compile on Windows (Clang 18+ with MSVC toolchain) due to:
char* to typed pointer)
Changes
Main repo:
Submodule patch (windows-tl2-build-fixes.patch, apply to 3rdparty/llama.cpp):
Test plan