b1876 #73
Merged
b1876 #73
Conversation
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
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* imatrix: load * imatrix: WIP * imatrix: Add Q2_K quantization * imatrix: also guard against Q2_K_S quantization without importance matrix * imatrix: guard even more against low-bit quantization misuse --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Correctly set support_simdgroup_reduction and support_simdgroup_mm on iPhone/iPad * log a little bit more info on iOS
* Fix ffn_down quantization mix for MoE models In #4872 I did not consider the part where every third tensor is quantized with more bits. Fir MoE this leads to tensors of the same layer being quantized with different number of bits, which is not considered as a possibility in the inference implementation (it is assumed all experts use the same quantization). * Fix the fix * Review suggestion --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* llama : minor fix indent * llama : check LLAMA_TRACE env for extra logging ggml-ci
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 21, 2024
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 21, 2024
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 22, 2024
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 22, 2024
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 25, 2024
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 25, 2024
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 25, 2024
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 25, 2024
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 25, 2024
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 25, 2024
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 26, 2024
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 27, 2024
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 27, 2024
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 27, 2024
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Dec 22, 2024
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Feb 25, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. * Speed up float -> iq4_nl conversion on CUDA --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 3, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 4, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 5, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 7, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 7, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 9, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 9, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 11, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 11, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 11, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 12, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 13, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 13, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 16, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 16, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 18, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 19, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 20, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 21, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 21, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 21, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 22, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 22, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 23, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 24, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 25, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 25, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 25, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 27, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Nexesenex
pushed a commit
that referenced
this pull request
Oct 28, 2025
* iqk_mul_mat: better iq4_nl implementation on Zen4/AVX2 PP-512 performance for LLaMA-3.1-8B goes to 162.6 t/s up from 133.2 t/s. Co-Authored-By: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
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.
No description provided.