Skip to content
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

Add support for GPTQ-quantized MoE models using MoE Marlin #2557

Merged
merged 1 commit into from
Sep 30, 2024
Merged

Add support for GPTQ-quantized MoE models using MoE Marlin #2557

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
15 changes: 8 additions & 7 deletions flake.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion flake.nix
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
inputs.nixpkgs.follows = "tgi-nix/nixpkgs";
};
nix-filter.url = "github:numtide/nix-filter";
tgi-nix.url = "github:huggingface/text-generation-inference-nix";
tgi-nix.url = "github:danieldk/tgi-nix/moe-kernels-0.4.0";
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

To be moved back on master no ?

Copy link
Member Author

@danieldk danieldk Sep 24, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yeah. On a branch to avoid accidentally updating the tgi-nix input, which would break MoE on TGI master (since 0.4.0 is an API break).

nixpkgs.follows = "tgi-nix/nixpkgs";
flake-utils.url = "github:numtide/flake-utils";
rust-overlay = {
Expand Down
89 changes: 89 additions & 0 deletions integration-tests/models/__snapshots__/test_flash_mixtral_gptq/test_flash_mixtral_gptq.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,89 @@
{
"details": {
"best_of_sequences": null,
"finish_reason": "length",
"generated_tokens": 10,
"prefill": [
{
"id": 1,
"logprob": null,
"text": "<s>"
},
{
"id": 3735,
"logprob": -11.0078125,
"text": "Test"
},
{
"id": 2159,
"logprob": -13.59375,
"text": "request"
}
],
"seed": null,
"tokens": [
{
"id": 13,
"logprob": -1.7089844,
"special": false,
"text": "\n"
},
{
"id": 13,
"logprob": -0.68847656,
"special": false,
"text": "\n"
},
{
"id": 28771,
"logprob": -1.9394531,
"special": false,
"text": "#"
},
{
"id": 3735,
"logprob": -2.8808594,
"special": false,
"text": " Test"
},
{
"id": 2159,
"logprob": -0.37280273,
"special": false,
"text": " request"
},
{
"id": 13,
"logprob": -0.26098633,
"special": false,
"text": "\n"
},
{
"id": 13,
"logprob": -0.0017137527,
"special": false,
"text": "\n"
},
{
"id": 1064,
"logprob": -2.2695312,
"special": false,
"text": "##"
},
{
"id": 3735,
"logprob": -1.9238281,
"special": false,
"text": " Test"
},
{
"id": 2159,
"logprob": -0.48828125,
"special": false,
"text": " request"
}
],
"top_tokens": null
},
"generated_text": "\n\n# Test request\n\n## Test request"
}
89 changes: 89 additions & 0 deletions ...ests/models/__snapshots__/test_flash_mixtral_gptq/test_flash_mixtral_gptq_all_params.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,89 @@
{
"details": {
"best_of_sequences": null,
"finish_reason": "length",
"generated_tokens": 10,
"prefill": [
{
"id": 1,
"logprob": null,
"text": "<s>"
},
{
"id": 3735,
"logprob": -11.0078125,
"text": "Test"
},
{
"id": 2159,
"logprob": -13.59375,
"text": "request"
}
],
"seed": 0,
"tokens": [
{
"id": 13,
"logprob": -0.34838867,
"special": false,
"text": "\n"
},
{
"id": 13940,
"logprob": -0.38916016,
"special": false,
"text": "``"
},
{
"id": 28832,
"logprob": 0.0,
"special": false,
"text": "`"
},
{
"id": 3371,
"logprob": -1.2529297,
"special": false,
"text": "json"
},
{
"id": 13,
"logprob": 0.0,
"special": false,
"text": "\n"
},
{
"id": 28751,
"logprob": 0.0,
"special": false,
"text": "{"
},
{
"id": 13,
"logprob": 0.0,
"special": false,
"text": "\n"
},
{
"id": 2287,
"logprob": 0.0,
"special": false,
"text": " "
},
{
"id": 345,
"logprob": 0.0,
"special": false,
"text": " \""
},
{
"id": 3134,
"logprob": -0.640625,
"special": false,
"text": "request"
}
],
"top_tokens": null
},
"generated_text": "Test request\n```json\n{\n \"request"
}
Loading
Loading