Compilade/bitnet ternary #294
Merged
Conversation
This file contains 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
Not using a lookup table anymore makes it match q4_0 speed. * gguf-py : fix formatting * llama : remove spaces on empty line
This makes the 1.625 bpw type go faster than q4_0. Still not the fastest.
This still results in the exact same tensor weights and scales, but it reveals some weirdness in the current algorithm.
Its FFN size is 5460 which is not convenient. The offending tensors are kept in F16, which makes the final model 5.01 bpw.
Same optimization as for TQ2_0 by offsetting the sum instead of the weights. This makes TQ1_0 almost as fast as Q8_0 on AVX2.
The compiler seems smart enough to use the same instruction even when using vget_high_s8 instead.
* llama : remove the separate scale tensors of BitNet b1.58 They won't be needed, since the remaining ternary quant types have built-in scales.
Not yet tested on harware which supports it, might not work or might not even compile. But also it might. It should make the performance better on recent ARM CPUs. * ggml-quants : remove comment about possible format change of TQ2_0 Making it slightly more convenient for AVX512 but less convenient for everything else is not worth the trouble.
…ronization overhead. (#8943) * Optimize Vulkan backend for better CPU performance and less GPU synchronization overhead. - Allocation overhead for the temporary std::vectors was easily detectable with a sampling profiler and simple to remove. - ggml_vk_sync_buffer introduce a full pipeline sync which has a significant cost on the GPU side, sometimes larger than the actual kernel execution. Adding only barriers for shader read/writes and transfers seems to be sufficient looking at the code which either launches compute kernels or copies tensors. * Fix small typo --------- Co-authored-by: 0cc4m <[email protected]>
…8956) Co-authored-by: Stanisław Szymczyk <[email protected]>
Co-authored-by: Neo Zhang <>
* gguf-py : Numpy dequantization for most types * gguf-py : Numpy dequantization for grid-based i-quants
* ggml-quants : use roundf instead of nearest_int for TQ1_0 and TQ2_0 This does not change anything for ternary models, since their values should never end up being in halfway cases anyway.
* py : fix requirements check '==' -> '~=' * cont : fix the fix * ci : run on all requirements.txt
Fixes: https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=70724 In order to access the above bug you need to login using one of the emails in https://github.com/google/oss-fuzz/blob/master/projects/llamacpp/project.yaml#L3-L5 Signed-off-by: David Korczynski <[email protected]>
Fixes: https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=70680 Signed-off-by: David Korczynski <[email protected]>
* readme: introduce gpustack GPUStack is an open-source GPU cluster manager for running large language models, which uses llama.cpp as the backend. Signed-off-by: thxCode <[email protected]> * readme: introduce gguf-parser GGUF Parser is a tool to review/check the GGUF file and estimate the memory usage without downloading the whole model. Signed-off-by: thxCode <[email protected]> --------- Signed-off-by: thxCode <[email protected]>
* llama : model-based max number of graph nodes calculation * Update src/llama.cpp --------- Co-authored-by: slaren <[email protected]>
Signed-off-by: Diogo Teles Sant'Anna <[email protected]>
* ggml : move rope type enum to ggml.h This commit moves the `llama_rope_type` enum from `llama.h` to `ggml.h` and changes its name to `ggml_rope_type`. The motivation for this change is to address the TODO in `llama.h` and use the enum in ggml. Note: This commit does not change the `mode` parameter to be of type `enum ggml_rope_type`. The name `mode` and its usage suggest that it might be more generic and possibly used as a bit field for multiple flags. Further investigation/discussion may be needed to determine if `mode` should be restricted to RoPE types. * squash! ggml : move rope type enum to ggml.h This commit removes GGML_ROPE_TYPE_NONE and GGML_ROPE_TYPE_GLM from ggml.h, and back the llama_rope_type enum. I've kept the assert for GGML_ROPE_TYPE_GLM as I'm not sure if it is safe to remove it yet. * squash! ggml : move rope type enum to ggml.h This commit removes the enum ggml_rope_type from ggml.h and replaces it with a define (GGML_ROPE_TYPE_NEOX). This define is used in the code to check if the mode is set to GPT-NeoX. Also the enum llama_rope_type has been updated to reflect this change. * squash! ggml : move rope type enum to ggml.h This commit contains a suggestion enable the GGML_ROPE_TYPE_NEOX macro/define to be passed to the shader compiler. * squash! ggml : move rope type enum to ggml.h This commit fixes the editorconfig-checker warnings. * squash! ggml : move rope type enum to ggml.h Update comment for ggml_rope function. * Revert "squash! ggml : move rope type enum to ggml.h" This reverts commit 6261222. * squash! ggml : move rope type enum to ggml.h Add GGML_ROPE_TYPE_NEOX to rope_common.comp. * remove extra line --------- Co-authored-by: slaren <[email protected]>
The token embeddings and output tensors are kept in F16 to allow quantizing them to Q4_K and Q6_K with llama-quantize. * llama : handle fallback for TQ1_0 and TQ2_0 with Q4_0 Q4_0 is not completely symmetric (so not lossless for ternary models), but it should be good enough.
github-actions
bot
added
documentation
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.
No description provided.