biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI/Build] Add Qwen2.5-VL-7B-Instruct ChartQA Accuracy Tests in CI (#21810)

Browse Source 
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Signed-off-by: zhewenli <zhewenli@meta.com>
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>
Co-authored-by: Ye (Charlotte) Qi <ye.charlotte.qi@gmail.com>
This commit is contained in:
Zhewen Li
2025-10-15 01:09:56 -07:00
committed by GitHub
parent f5ed68ef63
commit f3c378ffa7
13 changed files with 164 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-QQQ.yaml Normal file
View File

@@ -0,0 +1,12 @@
# For vllm script, with -t option (tensor parallel size).
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m HandH1998/QQQ-Llama-3-8b-g128 -b 32 -l 1000 -f 5 -t 1
model_name: "HandH1998/QQQ-Llama-3-8b-g128"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.419
- name: "exact_match,flexible-extract"
value: 0.416
limit: 1000
num_fewshot: 5

11
.buildkite/lm-eval-harness/configs/Meta-Llama-4-Maverick-17B-128E-Instruct-FP8-MM.yaml Normal file
View File

@@ -0,0 +1,11 @@
# For hf script, without -t option (tensor parallel size).
# bash .buildkite/lm-eval-harness/run-lm-eval-chartqa-vllm-vlm-baseline.sh -m meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 -b 32 -l 100 -t 8
model_name: "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
backend: "vllm-vlm"
tasks:
- name: "chartqa"
metrics:
- name: "relaxed_accuracy,none"
value: 0.90
limit: 100
num_fewshot: 0

11
.buildkite/lm-eval-harness/configs/Meta-Llama-4-Maverick-17B-128E-Instruct-FP8.yaml Normal file
View File

@@ -0,0 +1,11 @@
# For hf script, without -t option (tensor parallel size).
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 -b 32 -l 250 -t 8 -f 5
model_name: "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
backend: "vllm-vlm"
tasks:
- name: "mmlu_pro"
metrics:
- name: "exact_match,custom-extract"
value: 0.80
limit: 250 # will run on 250 * 14 subjects = 3500 samples
num_fewshot: 5

3
.buildkite/lm-eval-harness/configs/Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
View File

@@ -1,4 +1,5 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m RedHatAI/Qwen2.5-VL-3B-Instruct-FP8-Dynamic -b auto -l 1319 -f 5 -t 1
# For vllm script, with -t option (tensor parallel size)
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m RedHatAI/Qwen2.5-VL-3B-Instruct-FP8-Dynamic -l 1319 -t 1
model_name: "RedHatAI/Qwen2.5-VL-3B-Instruct-FP8-Dynamic"
tasks:
- name: "gsm8k"

12
.buildkite/lm-eval-harness/configs/Qwen2.5-VL-7B-Instruct.yaml Normal file
View File

@@ -0,0 +1,12 @@
# For vllm script, with -t option (tensor parallel size).
# bash .buildkite/lm-eval-harness/run-lm-eval-chartqa-vllm-vlm-baseline.sh -m Qwen/Qwen2.5-VL-7B-Instruct -l 2500 -t 1
model_name: "Qwen/Qwen2.5-VL-7B-Instruct"
backend: "vllm-vlm"
tasks:
- name: "chartqa"
metrics:
- name: "relaxed_accuracy,none"
value: 0.855
limit: 2500
num_fewshot: 0

1
.buildkite/lm-eval-harness/configs/models-large-h100.txt Normal file
View File

@@ -0,0 +1 @@
Meta-Llama-4-Maverick-17B-128E-Instruct-FP8.yaml

1
.buildkite/lm-eval-harness/configs/models-mm-large-h100.txt Normal file
View File

@@ -0,0 +1 @@
Meta-Llama-4-Maverick-17B-128E-Instruct-FP8-MM.yaml

1
.buildkite/lm-eval-harness/configs/models-mm-small.txt Normal file
View File

@@ -0,0 +1 @@
Qwen2.5-VL-7B-Instruct.yaml