gguf-py : simplify support for quant types #8838
Merged
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
compilade
commented
Aug 2, 2024
gguf-py/gguf/constants.py
Outdated
Comment on lines
1199
to
1237
| # Default quantization type for each file type | ||
| # Keep this the same as in llama_model_quantize_internal from llama.cpp | ||
| LlamaFileTypeMap: dict[LlamaFileType, GGMLQuantizationType] = { | ||
| LlamaFileType.MOSTLY_Q4_0: GGMLQuantizationType.Q4_0, | ||
| LlamaFileType.MOSTLY_Q4_1: GGMLQuantizationType.Q4_1, | ||
| LlamaFileType.MOSTLY_Q5_0: GGMLQuantizationType.Q5_0, | ||
| LlamaFileType.MOSTLY_Q5_1: GGMLQuantizationType.Q5_1, | ||
| LlamaFileType.MOSTLY_Q8_0: GGMLQuantizationType.Q8_0, | ||
| LlamaFileType.MOSTLY_F16: GGMLQuantizationType.F16, | ||
| LlamaFileType.MOSTLY_BF16: GGMLQuantizationType.BF16, | ||
| LlamaFileType.ALL_F32: GGMLQuantizationType.F32, | ||
|
|
||
| # K-quants | ||
| LlamaFileType.MOSTLY_Q2_K_S: GGMLQuantizationType.Q2_K, | ||
| LlamaFileType.MOSTLY_Q2_K: GGMLQuantizationType.Q2_K, | ||
| LlamaFileType.MOSTLY_IQ3_XS: GGMLQuantizationType.IQ3_S, | ||
| LlamaFileType.MOSTLY_Q3_K_S: GGMLQuantizationType.Q3_K, | ||
| LlamaFileType.MOSTLY_Q3_K_M: GGMLQuantizationType.Q3_K, | ||
| LlamaFileType.MOSTLY_Q3_K_L: GGMLQuantizationType.Q3_K, | ||
| LlamaFileType.MOSTLY_Q4_K_S: GGMLQuantizationType.Q4_K, | ||
| LlamaFileType.MOSTLY_Q4_K_M: GGMLQuantizationType.Q4_K, | ||
| LlamaFileType.MOSTLY_Q5_K_S: GGMLQuantizationType.Q5_K, | ||
| LlamaFileType.MOSTLY_Q5_K_M: GGMLQuantizationType.Q5_K, | ||
| LlamaFileType.MOSTLY_Q6_K: GGMLQuantizationType.Q6_K, | ||
| LlamaFileType.MOSTLY_IQ2_XXS: GGMLQuantizationType.IQ2_XXS, | ||
| LlamaFileType.MOSTLY_IQ2_XS: GGMLQuantizationType.IQ2_XS, | ||
| LlamaFileType.MOSTLY_IQ2_S: GGMLQuantizationType.IQ2_XS, | ||
| LlamaFileType.MOSTLY_IQ2_M: GGMLQuantizationType.IQ2_S, | ||
| LlamaFileType.MOSTLY_IQ3_XXS: GGMLQuantizationType.IQ3_XXS, | ||
| LlamaFileType.MOSTLY_IQ1_S: GGMLQuantizationType.IQ1_S, | ||
| LlamaFileType.MOSTLY_IQ1_M: GGMLQuantizationType.IQ1_M, | ||
| LlamaFileType.MOSTLY_IQ4_NL: GGMLQuantizationType.IQ4_NL, | ||
| LlamaFileType.MOSTLY_IQ4_XS: GGMLQuantizationType.IQ4_XS, | ||
| LlamaFileType.MOSTLY_IQ3_S: GGMLQuantizationType.IQ3_S, | ||
| LlamaFileType.MOSTLY_IQ3_M: GGMLQuantizationType.IQ3_S, | ||
| LlamaFileType.MOSTLY_Q4_0_4_4: GGMLQuantizationType.Q4_0_4_4, | ||
| LlamaFileType.MOSTLY_Q4_0_4_8: GGMLQuantizationType.Q4_0_4_8, | ||
| LlamaFileType.MOSTLY_Q4_0_8_8: GGMLQuantizationType.Q4_0_8_8, | ||
| } |
There was a problem hiding this comment.
I'm adding this because it's now used in convert_hf_to_gguf.py to get the default quantization type from a file type, but I'm not sure if the file types which are not used in the convert script should still be mapped.
Anyone has an opinion on that?
There was a problem hiding this comment.
In general we should avoid coupling gguf with llama.cpp specifically. The llama_ftype enum is specific to llama.cpp so maybe it would be better to avoid it
There was a problem hiding this comment.
Maybe at some point we should move the LlamaFileType enum from gguf-py/gguf/constants.py to a new llama.cpp/constants.py and this file can hold the llama.cpp-specific file type logic and potentially other stuff
15 tasks
Too specific to 'llama.cpp', and would be a maintenance burden to keep up to date. * gguf-py : add generic quantize and dequantize functions The quant classes no longer need to be known, only the target or the source type, for 'quantize' and 'dequantize', respectively.
ggerganov
approved these changes
Aug 4, 2024
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Nov 15, 2024
* gguf-py : use classes for quants * convert_hf : simplify internal quantization type selection * gguf-py : fix flake8 lint * gguf-py : fix BF16 numpy view type * gguf-py : remove LlamaFileTypeMap Too specific to 'llama.cpp', and would be a maintenance burden to keep up to date. * gguf-py : add generic quantize and dequantize functions The quant classes no longer need to be known, only the target or the source type, for 'quantize' and 'dequantize', respectively.
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Nov 18, 2024
* gguf-py : use classes for quants * convert_hf : simplify internal quantization type selection * gguf-py : fix flake8 lint * gguf-py : fix BF16 numpy view type * gguf-py : remove LlamaFileTypeMap Too specific to 'llama.cpp', and would be a maintenance burden to keep up to date. * gguf-py : add generic quantize and dequantize functions The quant classes no longer need to be known, only the target or the source type, for 'quantize' and 'dequantize', respectively.
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.
There are only 2 types right now supported by
gguf-py/gguf/quants.py(BF16andQ8_0), but there will be more over time, especially for dequantization, because this could enable interesting things as in #8831Here, I'm reducing the quant-type-specific code needed to be written by using an abstract base class.
I've also simplified the type selection logic in
convert_hf_to_gguf.py, which should allow making overrides like in #8715 simpler to implement in a more maintainable way.I've tested with https://huggingface.co/Qwen/Qwen2-0.5B-Instruct that conversion with
convert_hf_to_gguf.pyis still the same as when usingllama-quantizefrom a F32 conversion.The files ending with
-qwere made withllama-quantize.I've also tested https://huggingface.co/state-spaces/mamba-130m-hf: