Update state dict and model together #573
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
facebook-github-bot
added
the
CLA Signed
metascroy
approved these changes
Apr 30, 2024
jerryzh168
reviewed
May 1, 2024
Comment on lines
+81
to
+82
| weight_scale=scales.float(), | ||
| weight_zero_point=0, |
There was a problem hiding this comment.
these two has to either both be tensor or both be scalar, it should work if you do scales.float().item() I think
There was a problem hiding this comment.
Wait... This is a vector of 32000 elements
There was a problem hiding this comment.
oh but _qdq_dynamic_quantized_linear only supports per tensor quantization, then you may want to call a different op in that function
to align the size you could do: weight_zero_point = torch.zeros(scales.shape)
malfet
pushed a commit
that referenced
this pull request
Jul 17, 2024
* code beautification * code beautification, move functions together * rewrite model rewriter * rewrite quantizers * weights is none check * typo * not weight -> weight is not None * fix dimensions for parallel prefill * test * typo * bfloat16 on ARM with MacOS 14 * precision for a8w4 * sdpa_kv * fixes * inline qlq definition * trial and error * qdq not working * ci * not so fast with bf16=fast * typo, and handle fast across maxcos version... * typo * type cast
malfet
pushed a commit
that referenced
this pull request
Jul 17, 2024
* code beautification * code beautification, move functions together * rewrite model rewriter * rewrite quantizers * weights is none check * typo * not weight -> weight is not None * fix dimensions for parallel prefill * test * typo * bfloat16 on ARM with MacOS 14 * precision for a8w4 * sdpa_kv * fixes * inline qlq definition * trial and error * qdq not working * ci * not so fast with bf16=fast * typo, and handle fast across maxcos version... * typo * type cast
malfet
pushed a commit
that referenced
this pull request
Jul 17, 2024
* code beautification * code beautification, move functions together * rewrite model rewriter * rewrite quantizers * weights is none check * typo * not weight -> weight is not None * fix dimensions for parallel prefill * test * typo * bfloat16 on ARM with MacOS 14 * precision for a8w4 * sdpa_kv * fixes * inline qlq definition * trial and error * qdq not working * ci * not so fast with bf16=fast * typo, and handle fast across maxcos version... * typo * type cast
malfet
pushed a commit
that referenced
this pull request
Jul 17, 2024
* code beautification * code beautification, move functions together * rewrite model rewriter * rewrite quantizers * weights is none check * typo * not weight -> weight is not None * fix dimensions for parallel prefill * test * typo * bfloat16 on ARM with MacOS 14 * precision for a8w4 * sdpa_kv * fixes * inline qlq definition * trial and error * qdq not working * ci * not so fast with bf16=fast * typo, and handle fast across maxcos version... * typo * type cast
malfet
pushed a commit
that referenced
this pull request
Jul 17, 2024
* code beautification * code beautification, move functions together * rewrite model rewriter * rewrite quantizers * weights is none check * typo * not weight -> weight is not None * fix dimensions for parallel prefill * test * typo * bfloat16 on ARM with MacOS 14 * precision for a8w4 * sdpa_kv * fixes * inline qlq definition * trial and error * qdq not working * ci * not so fast with bf16=fast * typo, and handle fast across maxcos version... * typo * type cast
malfet
pushed a commit
that referenced
this pull request
Jul 17, 2024
* code beautification * code beautification, move functions together * rewrite model rewriter * rewrite quantizers * weights is none check * typo * not weight -> weight is not None * fix dimensions for parallel prefill * test * typo * bfloat16 on ARM with MacOS 14 * precision for a8w4 * sdpa_kv * fixes * inline qlq definition * trial and error * qdq not working * ci * not so fast with bf16=fast * typo, and handle fast across maxcos version... * typo * type cast
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.
Update state dict and model together