EngineX-Mthreads/enginex-mthreads-vllm
4
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Sync from v0.13

Browse Source
This commit is contained in:
xiezhongtao
2026-01-19 10:38:50 +08:00
parent b2ef04d792
commit 5aef6c175a
3714 changed files with 854317 additions and 89342 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/evals/gsm8k/configs/DeepSeek-V2-Lite-Instruct-FP8.yaml Normal file
View File

@@ -0,0 +1,6 @@
model_name: "RedHatAI/DeepSeek-Coder-V2-Lite-Instruct-FP8"
accuracy_threshold: 0.72
num_questions: 1319
num_fewshot: 5
max_model_len: 4096

5
tests/evals/gsm8k/configs/Llama-3-8B-Instruct-nonuniform-CT.yaml Normal file
View File

@@ -0,0 +1,5 @@
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test"
accuracy_threshold: 0.74
num_questions: 1319
num_fewshot: 5
max_model_len: 4096

5
tests/evals/gsm8k/configs/Llama-3.2-1B-Instruct-INT8-CT.yaml Normal file
View File

@@ -0,0 +1,5 @@
model_name: "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8"
accuracy_threshold: 0.31
num_questions: 1319
num_fewshot: 5
max_model_len: 4096

5
tests/evals/gsm8k/configs/Qwen1.5-MoE-W4A16-CT.yaml Normal file
View File

@@ -0,0 +1,5 @@
model_name: "nm-testing/Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16"
accuracy_threshold: 0.45
num_questions: 1319
num_fewshot: 5
max_model_len: 4096

5
tests/evals/gsm8k/configs/Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml Normal file
View File

@@ -0,0 +1,5 @@
model_name: "RedHatAI/Qwen2.5-VL-3B-Instruct-FP8-Dynamic"
accuracy_threshold: 0.60
num_questions: 1319
num_fewshot: 5
max_model_len: 4096

5
tests/evals/gsm8k/configs/Qwen3-0.6B-FP8.yaml Normal file
View File

@@ -0,0 +1,5 @@
model_name: "Qwen/Qwen3-0.6B-FP8"
accuracy_threshold: 0.375
num_questions: 1319
num_fewshot: 5
max_model_len: 4096

6
tests/evals/gsm8k/configs/Qwen3-30B-A3B-NVFP4.yaml Normal file
View File

@@ -0,0 +1,6 @@
model_name: "nvidia/Qwen3-30B-A3B-FP4"
accuracy_threshold: 0.89
num_questions: 1319
num_fewshot: 5
max_model_len: 4096

5
tests/evals/gsm8k/configs/models-blackwell.txt Normal file
View File

@@ -0,0 +1,5 @@
Qwen3-0.6B-FP8.yaml
Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
Qwen1.5-MoE-W4A16-CT.yaml
DeepSeek-V2-Lite-Instruct-FP8.yaml
Qwen3-30B-A3B-NVFP4.yaml

6
tests/evals/gsm8k/configs/models-small.txt Normal file
View File

@@ -0,0 +1,6 @@
Qwen3-0.6B-FP8.yaml
Llama-3.2-1B-Instruct-INT8-CT.yaml
Llama-3-8B-Instruct-nonuniform-CT.yaml
Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
Qwen1.5-MoE-W4A16-CT.yaml
DeepSeek-V2-Lite-Instruct-FP8.yaml