Skip to content

refine md tables #994

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 9 commits into from
Nov 7, 2025
Merged

refine md tables #994

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
719e5ab
fp8 exporting bugfix
WeiweiZhang1 Oct 9, 2025
8e8b04f
Merge branch 'main' of https://github.com/intel/auto-round into main
WeiweiZhang1 Oct 16, 2025
045d3a2
Update mxnv_acc.md
WeiweiZhang1 Nov 5, 2025
57842a1
Merge branch 'main' of https://github.com/intel/auto-round into main
WeiweiZhang1 Nov 6, 2025
c2daa79
refine exllama backend cuda UT
WeiweiZhang1 Nov 6, 2025
cfa79d3
Merge branch 'refine-doc-table' of https://github.com/intel/auto-roun…
WeiweiZhang1 Nov 6, 2025
018bb0f
refine md tables
WeiweiZhang1 Nov 6, 2025
a630771
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Nov 6, 2025
008e480
revert typo
WeiweiZhang1 Nov 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions docs/alg_202508.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,11 +4,11 @@ in [modeling_llama.py](https://github.com/huggingface/transformers/blob/main/src
to stabilize accuracy during evaluation. All other settings follow the default configurations of AutoRound and lm-eval.

| Qwen3-8B W2G64 | Avg. | arc_challenge | hellaswag | gsm8k | lambada_openai | mmlu | mmlupro | truthfulqa_mc1 | winogrande |
|-------------------|--------|---------------|-----------|--------|----------------|--------|---------|----------------|------------|
| AutoRound | 0.4373 | 0.4019 | 0.4437 | 0.4215 | 0.4826 | 0.5474 | 0.263 | 0.3072 | 0.6314 |
|:-------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|
| AutoRound | 0.4373 | 0.4019 | 0.4437 | 0.4215 | 0.4826 | 0.5474 | 0.2630 | 0.3072 | 0.6314 |
| AutoRound+alg_ext | 0.4787 | 0.4275 | 0.4516 | 0.5944 | 0.5181 | 0.5773 | 0.2807 | 0.3305 | 0.6496 |

| Llama3.1-8B W2G64 | Avg. | arc_challenge | hellaswag | gsm8k | lambada_openai | mmlu | mmlupro | truthfulqa_mc1 | winogrande |
|-------------------|--------|---------------|-----------|--------|----------------|--------|---------|----------------|------------|
| AutoRound | 0.382 | 0.3635 | 0.4562 | 0.1622 | 0.5069 | 0.4411 | 0.1661 | 0.3207 | 0.6393 |
| AutoRound+alg_ext | 0.4166 | 0.3712 | 0.4729 | 0.2039 | 0.5946 | 0.4981 | 0.2163 | 0.3011 | 0.6748 |
|:-------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|
| AutoRound | 0.3820 | 0.3635 | 0.4562 | 0.1622 | 0.5069 | 0.4411 | 0.1661 | 0.3207 | 0.6393 |
| AutoRound+alg_ext | 0.4166 | 0.3712 | 0.4729 | 0.2039 | 0.5946 | 0.4981 | 0.2163 | 0.3011 | 0.6748 |
10 changes: 5 additions & 5 deletions docs/auto_scheme_acc.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ For mxfp experiment, we use fake model while for weight only model we use real m
### Table 1 MXFP4/8 mixed accuracy.

| Average bits | Llama3.1-8B-I | Qwen2.5-7B-I | Qwen3-8B | Qwen3-32B |
|------------------|----------------|----------------|----------------|----------------|
|:------------------|:----------------:|:----------------:|:----------------:|:----------------:|
| **BF16** | 0.7076 (100%) | 0.7075 (100%) | 0.6764 (100%) | 0.7321 (100%) |
| **Pure 4-bit** | 0.6626 (93.6%) | 0.6550 (92.6%) | 0.6316 (93.4%) | 0.6901 (94.3%) |
| **Ours 4.5-bit** | 0.6808 (96.2%) | 0.6776 (95.8%) | 0.6550 (96.8%) | 0.7176 (98.0%) |
Expand All @@ -27,15 +27,15 @@ performance advantages.
### Table 2 Comparison with other recipes at an average of 5 bits of mxfp datatype

| Avg. bits = 5 | Llama3.1-8B-I | Qwen2.5-7B-I | Qwen3-8B |
|-----------------------|-------------------:|-------------------:|-------------------:|
|:------------------|:----------------:|:----------------:|:----------------:|
| **Tail layers 8-bit** | 0.6671 (94.3%) | 0.6616 (93.5%) | 0.6410 (94.8%) |
| **Head layers 8-bit** | 0.6657 (94.1%) | 0.6686 (94.5%) | 0.6356 (94.0%) |
| **Ours** | **0.6857 (96.9%)** | **0.6823 (96.4%)** | **0.6594 (97.5%)** |

### Table 3 Comparison with other recipes at an average of 4.5 bits of mxfp datatype

| Avg. bits = 4.5 | Llama3.1-8B-I | Qwen2.5-7B-I | Qwen3-8B |
|-----------------------|-------------------:|-------------------:|-------------------:|
|:------------------|:----------------:|:----------------:|:----------------:|
| **Tail layers 8-bit** | 0.6614 (93.5%) | 0.6535 (92.4%) | 0.6373 (94.2%) |
| **Head layers 8-bit** | 0.6568 (92.8%) | 0.6642 (93.9%) | 0.6305 (93.2%) |
| **Ours** | **0.6808 (96.2%)** | **0.6776 (95.5%)** | **0.6550 (95.8%)** |
Expand All @@ -44,7 +44,7 @@ performance advantages.
### Table4 Comparison with other recipes at an average of 3 bits of W2G128 and W4G128

| Avg. bits = 4.5 | Llama3.1-8B-I | Qwen2.5-7B-I | Qwen3-8B |
|-----------------------|--------------:|-------------:|---------:|
|:------------------|:----------------:|:----------------:|:----------------:|
| **Tail layers 4-bit** | 0.6058 | 0.3798 | 0.4536 |
| **Head layers 4-bit** | 0.3198 | 0.3270 | 0.3196 |
| **Ours** | 0.6148 | 0.4058 | 0.4862 |
| **Ours** | 0.6148 | 0.4058 | 0.4862 |
16 changes: 8 additions & 8 deletions docs/mxnv_acc.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,13 +3,13 @@ Average accuracy of hellaswag,lambada_openai,mmlu,piqa,winogrande.
We evaluated using a fake model since we currently have no access to devices for running the real models. However, we have verified that in most cases the fake model closely matches the real model.

| mxfp4 g32 | llama3.1-8B-Instruct | Qwen2-7.5-Instruct | Phi4 | Qwen3-32B |
|-------------------|----------------------|--------------------|---------|-----------|
| RTN | 0.62124 | 0.65502 | 0.71674 | 0.69006 |
| AutoRound | 0.66862 | 0.67588 | 0.72472 | 0.72106 |
| AutoRound+alg_ext | 0.6732 | 0.68094 | 0.72252 | 0.72012 |
|:-------------------|:----------------------:|:--------------------:|:---------:|:-----------:|
| RTN | 0.6212 | 0.6550 | 0.7167 | 0.6901 |
| AutoRound | 0.6686 | 0.6758 | 0.7247 | 0.7211 |
| AutoRound+alg_ext | 0.6732 | 0.6809 | 0.7225 | 0.7201 |

| nvfp4 g16 | llama3.1-8B-Instruct | Qwen2-7.5-Instruct | Phi4 | Qwen3-32B |
|-------------------|----------------------|--------------------|---------|-----------|
| RTN | 0.68756 | 0.6906 | 0.72962 | 0.71636 |
| AutoRound | 0.69184 | 0.69728 | 0.73058 | 0.73062 |
| AutoRound+alg_ext | 0.69648 | 0.6989 | 0.7318 | 0.72948 |
|:-------------------|:----------------------:|:--------------------:|:---------:|:-----------:|
| RTN | 0.6876 | 0.6906 | 0.7296 | 0.7164 |
| AutoRound | 0.6918 | 0.6973 | 0.7306 | 0.7306 |
| AutoRound+alg_ext | 0.6965 | 0.6989 | 0.7318 | 0.7295 |