Add bitnet-embeddings-0.6b model adaptation and GGUF conversion tools#558
Open
isHuangXin wants to merge 2 commits into
Open
Add bitnet-embeddings-0.6b model adaptation and GGUF conversion tools#558isHuangXin wants to merge 2 commits into
isHuangXin wants to merge 2 commits into
Conversation
isHuangXin
commented
May 18, 2026
isHuangXin
commented
- Add GGUF conversion tool for bitnet-embeddings-0.6b (safetensors -> F16 GGUF and I2_S GGUF)
- Add Qwen3 architecture support in llama.cpp submodule with per-projection RMSNorm
- Add I2_S ternary quantization (2-bit packed -1/0/+1) for lossless precision
- Add f16 norm weight support for correct embedding inference
- Add benchmark and accuracy verification scripts
- Add GGUF layer inspection utilities for F16 and I2_S formats
- Add bitnet-lut-kernels.h placeholder for standalone compilation
- Update llama.cpp submodule to dev-bitnet-embedding-0.6b branch
Author
|
@microsoft-github-policy-service agree |
…nversion - Add GGUF conversion tool for bitnet-embeddings-0.6b (safetensors -> F16/I2_S GGUF) - Add Qwen3 architecture support in llama.cpp submodule with per-projection RMSNorm - Add I2_S ternary quantization (2-bit packed -1/0/+1) for lossless precision - Add f16 norm weight support for correct embedding inference - Add GGUF conversion documentation - Update llama.cpp submodule to dev-bitnet-embedding-0.6b branch
isHuangXin
force-pushed
the
dev-bitnet-embedding-0.6b
branch
from
f695806 to
28ef5f6
Compare
…endency - Add AVX512BW SIMD paths to ggml_vec_dot_i2_i8_s_1x1, _1xN, _Nx1 in ggml-bitnet-mad.cpp, processing 2 I2_S blocks per iteration with 512-bit registers for ~2x throughput on AVX512-capable CPUs - Guard #include "bitnet-lut-kernels.h" in ggml-bitnet-lut.cpp with TL1/TL2 preprocessor checks so I2_S builds no longer require the auto-generated header
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
1 participant
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.