EngineX-Cambricon/enginex-mlu370-vllm
11
0
Fork 1
Code Issues Pull Requests Actions Projects Releases Wiki Activity

add qwen3

Browse Source
This commit is contained in:
Chranos
2026-02-04 17:22:39 +08:00
parent d1c0f68ab4
commit 8511fe8530
1932 changed files with 300426 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/DeepSeek-V2-Lite-Chat.yaml Normal file
View File

@@ -0,0 +1,12 @@
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m deepseek-ai/DeepSeek-V2-Lite-Chat -b "auto" -l 1000 -f 5 -t 2
model_name: "deepseek-ai/DeepSeek-V2-Lite-Chat"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.671
- name: "exact_match,flexible-extract"
value: 0.664
limit: 1000
num_fewshot: 5
trust_remote_code: True

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh -m nm-testing/Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform -b auto -l 1000 -f 5
model_name: "nm-testing/Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.905
- name: "exact_match,flexible-extract"
value: 0.905
limit: 1000
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Meta-Llama-3-70B-Instruct.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh -m meta-llama/Meta-Llama-3-70B-Instruct -b 32 -l 250 -f 5
model_name: "meta-llama/Meta-Llama-3-70B-Instruct"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.892
- name: "exact_match,flexible-extract"
value: 0.892
limit: 250
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct-Channelwise-compressed-tensors.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors -b auto -l 1000 -f 5 -t 1
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.752
- name: "exact_match,flexible-extract"
value: 0.754
limit: 1000
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform -b auto -l 1000 -f 5 -t 1
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.753
- name: "exact_match,flexible-extract"
value: 0.753
limit: 1000
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct-FP8-compressed-tensors.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test -b 32 -l 1000 -f 5 -t 1
model_name: "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.755
- name: "exact_match,flexible-extract"
value: 0.755
limit: 1000
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct-FP8.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Meta-Llama-3-8B-Instruct-FP8 -b 32 -l 250 -f 5 -t 1
model_name: "neuralmagic/Meta-Llama-3-8B-Instruct-FP8"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.753
- name: "exact_match,flexible-extract"
value: 0.753
limit: 1000
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct-INT8-compressed-tensors-asym.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test -b "auto" -l 250 -f 5 -t 1
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.764
- name: "exact_match,flexible-extract"
value: 0.764
limit: 250
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct-INT8-compressed-tensors.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test -b "auto" -l 250 -f 5 -t 1
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.728
- name: "exact_match,flexible-extract"
value: 0.728
limit: 250
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct-nonuniform-compressed-tensors.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test -b auto -l 1000 -f 5 -t 1
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.758
- name: "exact_match,flexible-extract"
value: 0.759
limit: 1000
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh -m meta-llama/Meta-Llama-3-8B-Instruct -b 32 -l 250 -f 5 -t 1
model_name: "meta-llama/Meta-Llama-3-8B-Instruct"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.756
- name: "exact_match,flexible-extract"
value: 0.752
limit: 250
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-QQQ.yaml Normal file
View File

@@ -0,0 +1,11 @@
# 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
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Meta-Llama-3.2-1B-Instruct-INT8-compressed-tensors.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8 -b "auto" -l 1000 -f 5 -t 1
model_name: "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.356
- name: "exact_match,flexible-extract"
value: 0.358
limit: 1000
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Minitron-4B-Base-FP8.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m mgoin/Minitron-4B-Base-FP8 -b auto -l 1000 -f 5 -t 1
model_name: "mgoin/Minitron-4B-Base-FP8"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.233
- name: "exact_match,flexible-extract"
value: 0.236
limit: 1000
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Mixtral-8x22B-Instruct-v0.1-FP8-Dynamic.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Mixtral-8x22B-Instruct-v0.1-FP8-dynamic -b "auto" -l 250 -f 5 -t 8
model_name: "neuralmagic/Mixtral-8x22B-Instruct-v0.1-FP8-dynamic"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.86
- name: "exact_match,flexible-extract"
value: 0.86
limit: 250
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Mixtral-8x7B-Instruct-v0.1-FP8.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Mixtral-8x7B-Instruct-v0.1-FP8 -b "auto" -l 250 -f 5 -t 4
model_name: "neuralmagic/Mixtral-8x7B-Instruct-v0.1-FP8"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.624
- name: "exact_match,flexible-extract"
value: 0.624
limit: 250
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Mixtral-8x7B-Instruct-v0.1.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh -m neuralmagic/Mixtral-8x7B-Instruct-v0.1 -b 32 -l 250 -f 5 -t 4
model_name: "mistralai/Mixtral-8x7B-Instruct-v0.1"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.616
- name: "exact_match,flexible-extract"
value: 0.632
limit: 250
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Qwen2-1.5B-Instruct-FP8W8.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Qwen2-1.5B-Instruct-FP8W8 -b auto -l 1000 -f 5 -t 1
model_name: "nm-testing/Qwen2-1.5B-Instruct-FP8W8"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.578
- name: "exact_match,flexible-extract"
value: 0.585
limit: 1000
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Qwen2-1.5B-Instruct-INT8-compressed-tensors.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8 -b "auto" -l 1000 -f 5 -t 1
model_name: "neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.593
- name: "exact_match,flexible-extract"
value: 0.588
limit: 1000
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Qwen2-1.5B-Instruct-W8A16-compressed-tensors.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Qwen2-1.5B-Instruct-W8A16-Channelwise -b "auto" -l 1000 -f 5 -t 1
model_name: "nm-testing/Qwen2-1.5B-Instruct-W8A16-Channelwise"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.595
- name: "exact_match,flexible-extract"
value: 0.582
limit: 1000
num_fewshot: 5

11
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/Qwen2-57B-A14-Instruct.yaml Normal file
View File

@@ -0,0 +1,11 @@
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m Qwen/Qwen2-57B-A14B-Instruct -b "auto" -l 250 -f 5 -t 4
model_name: "Qwen/Qwen2-57B-A14B-Instruct"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.792
- name: "exact_match,flexible-extract"
value: 0.824
limit: 250
num_fewshot: 5

5
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/models-large.txt Normal file
View File

@@ -0,0 +1,5 @@
Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform.yaml
Meta-Llama-3-70B-Instruct.yaml
Mixtral-8x7B-Instruct-v0.1.yaml
Qwen2-57B-A14-Instruct.yaml
DeepSeek-V2-Lite-Chat.yaml

10
vllm-v0.6.2/.buildkite/lm-eval-harness/configs/models-small.txt Normal file
View File

@@ -0,0 +1,10 @@
Meta-Llama-3-8B-Instruct.yaml
Meta-Llama-3-8B-Instruct-FP8-compressed-tensors.yaml
Meta-Llama-3.2-1B-Instruct-INT8-compressed-tensors.yaml
Meta-Llama-3-8B-Instruct-INT8-compressed-tensors-asym.yaml
Meta-Llama-3-8B-Instruct-nonuniform-compressed-tensors.yaml
Meta-Llama-3-8B-Instruct-Channelwise-compressed-tensors.yaml
Minitron-4B-Base-FP8.yaml
Qwen2-1.5B-Instruct-INT8-compressed-tensors.yaml
Qwen2-1.5B-Instruct-FP8W8.yaml
Meta-Llama-3-8B-QQQ.yaml