You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
This is refactoring to follow new rule: "keep mlc-llm and tvm as clean as possible".
This commit removes several helper functions that were moved to slm/interface part.
This is refactoring to follow new rule: "keep mlc-llm and tvm as
clean as possible".
This commit removes several helper functions that were moved to
slm/interface part.
Hi, I tested it and I want to ask if the Smoothquant quantization really works? I run mlc_llm convert_weight ./dist/llama2 --quantization smq_q8i8f16_0 -o dist/$llama2-smq-MLC/ and get unquantized model. Weird.
Hi, I tested it and I want to ask if the Smoothquant quantization really works? I run mlc_llm convert_weight ./dist/llama2 --quantization smq_q8i8f16_0 -o dist/$llama2-smq-MLC/ and get unquantized model. Weird.
Hi @ponytaill ! It works, but not through the mlc-llm.
Hi, I tested it and I want to ask if the Smoothquant quantization really works? I run mlc_llm convert_weight ./dist/llama2 --quantization smq_q8i8f16_0 -o dist/$llama2-smq-MLC/ and get unquantized model. Weird.
Hi @ponytaill ! It works, but not through the mlc-llm.
Hi, thanks for your reply. Could you explain a little bit about how to use the code about Smoothquant without going through mlc-llm? I just started learning mlc-llm.
Hi, I tested it and I want to ask if the Smoothquant quantization really works? I run mlc_llm convert_weight ./dist/llama2 --quantization smq_q8i8f16_0 -o dist/$llama2-smq-MLC/ and get unquantized model. Weird.
Hi @ponytaill ! It works, but not through the mlc-llm.
Hi, thanks for your reply. Could you explain a little bit about how to use the code about Smoothquant without going through mlc-llm? I just started learning mlc-llm.
You need access to the private repo. If you don't have access, there's no way to run SmoothQuant in this case
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.
This is refactoring to follow new rule: "keep mlc-llm and tvm as clean as possible".
This commit removes several helper functions that were moved to slm/interface part.