Skip to content

feat: update other MoE models deps #2156

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

Jump to bottom
Merged
merged 5 commits into from
Nov 24, 2024
Merged

feat: update other MoE models deps #2156

merged 5 commits into from
Nov 24, 2024

Conversation

zhyncs
Copy link
Member

@zhyncs zhyncs commented Nov 24, 2024

Motivation

Modifications

Checklist

  • Format your code according to the Contributor Guide.
  • Add unit tests as outlined in the Contributor Guide.
  • Update documentation as needed, including docstrings or example tutorials.

@merrymercy
Copy link
Contributor

I left a few comments at #2153

@merrymercy
Copy link
Contributor

Rename

  • srt/layers/fused_moe -> srt/layers/fused_moe_grok
  • srt/layers/triton_fused_moe -> srt/layers/fused_moe_triton

Later, we will probably have srt/layers/fused_moe_turbomind. Then, all these files will be listed adjacently in alphabetical order.

@zhyncs
Copy link
Member Author

zhyncs commented Nov 24, 2024

I left a few comments at #2153

This part of the modification has been completed in this PR.

@zhyncs
Copy link
Member Author

zhyncs commented Nov 24, 2024

Rename

  • srt/layers/fused_moe -> srt/layers/fused_moe_grok
  • srt/layers/triton_fused_moe -> srt/layers/fused_moe_triton

Later, we will probably have srt/layers/fused_moe_turbomind. Then, all these files will be listed adjacently in alphabetical order.

I will not modify this part in this PR. It is expected to be updated in follow-up PRs later. The changes are simple, mainly verification. I might update it tomorrow or the day after.

@zhyncs
Copy link
Member Author

zhyncs commented Nov 24, 2024

Locally verified ok

[
  {
    "timestamp": "2024-11-24T04:59:08.994730",
    "model": "meta-llama/Llama-3.1-8B-Instruct",
    "metrics": {
      "en": 0.868,
      "en:std": 0.3384907679686405,
      "group_latin": 0.868,
      "group_latin:std": 0.3384907679686405,
      "score:std": 0.3384907679686405,
      "score": 0.868
    },
    "score": 0.868
  },
  {
    "timestamp": "2024-11-24T04:59:57.476733",
    "model": "mistralai/Mistral-7B-Instruct-v0.3",
    "metrics": {
      "en": 0.608,
      "en:std": 0.48819668167655544,
      "group_latin": 0.608,
      "group_latin:std": 0.48819668167655544,
      "score:std": 0.48819668167655544,
      "score": 0.608
    },
    "score": 0.608
  },
  {
    "timestamp": "2024-11-24T05:01:26.193959",
    "model": "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct",
    "metrics": {
      "en": 0.868,
      "en:std": 0.3384907679686405,
      "group_latin": 0.868,
      "group_latin:std": 0.3384907679686405,
      "score:std": 0.3384907679686405,
      "score": 0.868
    },
    "score": 0.868
  },
  {
    "timestamp": "2024-11-24T05:02:37.732333",
    "model": "google/gemma-2-27b-it",
    "metrics": {
      "en": 0.924,
      "en:std": 0.26499811320083017,
      "group_latin": 0.924,
      "group_latin:std": 0.26499811320083017,
      "score:std": 0.26499811320083017,
      "score": 0.924
    },
    "score": 0.924
  },
  {
    "timestamp": "2024-11-24T05:05:53.177669",
    "model": "meta-llama/Llama-3.1-70B-Instruct",
    "metrics": {
      "en": 0.976,
      "en:std": 0.15304901175767194,
      "group_latin": 0.976,
      "group_latin:std": 0.15304901175767194,
      "score:std": 0.15304901175767194,
      "score": 0.976
    },
    "score": 0.976
  },
  {
    "timestamp": "2024-11-24T05:08:29.849793",
    "model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
    "metrics": {
      "en": 0.656,
      "en:std": 0.4750410508577127,
      "group_latin": 0.656,
      "group_latin:std": 0.4750410508577127,
      "score:std": 0.4750410508577127,
      "score": 0.656
    },
    "score": 0.656
  },
  {
    "timestamp": "2024-11-24T05:12:54.222602",
    "model": "Qwen/Qwen2-57B-A14B-Instruct",
    "metrics": {
      "en": 0.884,
      "en:std": 0.320224920954007,
      "group_latin": 0.884,
      "group_latin:std": 0.320224920954007,
      "score:std": 0.320224920954007,
      "score": 0.884
    },
    "score": 0.884
  },
  {
    "timestamp": "2024-11-24T05:14:29.246964",
    "model": "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct",
    "metrics": {
      "en": 0.852,
      "en:std": 0.35509998591945907,
      "group_latin": 0.852,
      "group_latin:std": 0.35509998591945907,
      "score:std": 0.35509998591945907,
      "score": 0.852
    },
    "score": 0.852
  },
  {
    "timestamp": "2024-11-24T05:15:34.992883",
    "model": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8",
    "metrics": {
      "en": 0.864,
      "en:std": 0.3427885645700568,
      "group_latin": 0.864,
      "group_latin:std": 0.3427885645700568,
      "score:std": 0.3427885645700568,
      "score": 0.864
    },
    "score": 0.864
  },
  {
    "timestamp": "2024-11-24T05:16:33.803717",
    "model": "neuralmagic/Mistral-7B-Instruct-v0.3-FP8",
    "metrics": {
      "en": 0.56,
      "en:std": 0.4963869458396342,
      "group_latin": 0.56,
      "group_latin:std": 0.4963869458396342,
      "score:std": 0.4963869458396342,
      "score": 0.56
    },
    "score": 0.56
  },
  {
    "timestamp": "2024-11-24T05:18:15.019246",
    "model": "neuralmagic/DeepSeek-Coder-V2-Lite-Instruct-FP8",
    "metrics": {
      "en": 0.86,
      "en:std": 0.34698703145794946,
      "group_latin": 0.86,
      "group_latin:std": 0.34698703145794946,
      "score:std": 0.34698703145794946,
      "score": 0.86
    },
    "score": 0.86
  },
  {
    "timestamp": "2024-11-24T05:19:15.519638",
    "model": "neuralmagic/gemma-2-2b-it-FP8",
    "metrics": {
      "en": 0.64,
      "en:std": 0.48,
      "group_latin": 0.64,
      "group_latin:std": 0.48,
      "score:std": 0.48,
      "score": 0.64
    },
    "score": 0.64
  },
  {
    "timestamp": "2024-11-24T05:22:28.640542",
    "model": "neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8",
    "metrics": {
      "en": 0.964,
      "en:std": 0.18629009635512025,
      "group_latin": 0.964,
      "group_latin:std": 0.18629009635512025,
      "score:std": 0.18629009635512025,
      "score": 0.964
    },
    "score": 0.964
  },
  {
    "timestamp": "2024-11-24T05:25:07.266932",
    "model": "neuralmagic/Mixtral-8x7B-Instruct-v0.1-FP8",
    "metrics": {
      "en": 0.636,
      "en:std": 0.481148625686492,
      "group_latin": 0.636,
      "group_latin:std": 0.481148625686492,
      "score:std": 0.481148625686492,
      "score": 0.636
    },
    "score": 0.636
  },
  {
    "timestamp": "2024-11-24T05:28:10.900791",
    "model": "neuralmagic/Qwen2-72B-Instruct-FP8",
    "metrics": {
      "en": 0.956,
      "en:std": 0.20509509989270833,
      "group_latin": 0.956,
      "group_latin:std": 0.20509509989270833,
      "score:std": 0.20509509989270833,
      "score": 0.956
    },
    "score": 0.956
  },
  {
    "timestamp": "2024-11-24T05:30:46.679183",
    "model": "neuralmagic/Qwen2-57B-A14B-Instruct-FP8",
    "metrics": {
      "en": 0.844,
      "en:std": 0.3628553430776512,
      "group_latin": 0.844,
      "group_latin:std": 0.3628553430776512,
      "score:std": 0.3628553430776512,
      "score": 0.844
    },
    "score": 0.844
  },
  {
    "timestamp": "2024-11-24T05:32:36.080987",
    "model": "neuralmagic/DeepSeek-Coder-V2-Lite-Instruct-FP8",
    "metrics": {
      "en": 0.876,
      "en:std": 0.3295815528818322,
      "group_latin": 0.876,
      "group_latin:std": 0.3295815528818322,
      "score:std": 0.3295815528818322,
      "score": 0.876
    },
    "score": 0.876
  },
  {
    "timestamp": "2024-11-24T05:33:55.184910",
    "model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
    "metrics": {
      "en": 0.844,
      "en:std": 0.3628553430776512,
      "group_latin": 0.844,
      "group_latin:std": 0.3628553430776512,
      "score:std": 0.3628553430776512,
      "score": 0.844
    },
    "score": 0.844
  },
  {
    "timestamp": "2024-11-24T05:35:09.540475",
    "model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-GPTQ-INT4",
    "metrics": {
      "en": 0.844,
      "en:std": 0.3628553430776512,
      "group_latin": 0.844,
      "group_latin:std": 0.3628553430776512,
      "score:std": 0.3628553430776512,
      "score": 0.844
    },
    "score": 0.844
  }
]

@zhyncs zhyncs merged commit e3938b2 into main Nov 24, 2024
10 of 13 checks passed
@zhyncs zhyncs deleted the zhyncs/other branch November 24, 2024 13:36
timethink pushed a commit to timethink/sglang that referenced this pull request Mar 9, 2025
@zhyncs
feat: update other MoE models deps (sgl-project#2156)
b789841
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@merrymercy merrymercy Awaiting requested review from merrymercy merrymercy is a code owner

@Ying1123 Ying1123 Awaiting requested review from Ying1123 Ying1123 is a code owner

@hnyls2002 hnyls2002 Awaiting requested review from hnyls2002

@ispobock ispobock Awaiting requested review from ispobock ispobock is a code owner

@ByronHsu ByronHsu Awaiting requested review from ByronHsu

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@zhyncs @merrymercy