Skip to content

Commit

Permalink
rename models in benchmark dashboard's model mapping (#4608)
Browse files Browse the repository at this point in the history
In
pytorch/pytorch@88ef126,
I bumped the torchbench version, which includes some model names
updates:
- nanogpt_generate -> nanogpt (also supports train now)
- stable_diffusion -> stable_diffusion_text_encoder (now we've also
added the unet part of the model:
pytorch/benchmark@9cbeee3)

We need to update the model names for blueberries dashboard to track the
new models
  • Loading branch information
xmfan authored Oct 2, 2023
1 parent d2189b5 commit 9f460f7
Showing 1 changed file with 4 additions and 4 deletions.
8 changes: 4 additions & 4 deletions torchci/pages/benchmark/compilers.tsx
Original file line number Diff line number Diff line change
Expand Up @@ -1712,9 +1712,9 @@ export function AugmentData(data: CompilerPerformanceData[]) {
// _generate variants are good; they do E2E autoregressive
// generation and will induce varying context length.
"cm3leon_generate",
"nanogpt_generate",
"nanogpt",
"hf_T5_generate",
"nanogpt_generate",
"nanogpt",
// detection models are ok-ish; the good news is they call
// nonzero internally and exercise dynamic shapes that way,
// the bad news is we may not run enough iterations with
Expand Down Expand Up @@ -1743,12 +1743,12 @@ export function AugmentData(data: CompilerPerformanceData[]) {
},
blueberries: {
torchbench: new Set([
"nanogpt_generate",
"nanogpt",
"llama",
"llama_v2_7b_16h",
"sam",
"clip",
"stable_diffusion",
"stable_diffusion_text_encoder",
"hf_Whisper",
]),
},
Expand Down

1 comment on commit 9f460f7

@vercel
Copy link

@vercel vercel bot commented on 9f460f7 Oct 2, 2023

Choose a reason for hiding this comment

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

Please sign in to comment.