ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Add Meta-llama-3-8B-Instruct and Yi-6B-Chat to igpu nightly perf (#10810)

Browse source
This commit is contained in:
Yuwen Hu 2024-04-19 15:09:58 +08:00 committed by GitHub
parent fbd1743b5e
commit 07e8b045a9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 15 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
python/llm/test/benchmark/igpu-perf/1024-128.yaml
View file

@ -6,7 +6,7 @@ repo_id:
- 'internlm/internlm-chat-7b-8k' - 'internlm/internlm-chat-7b-8k'
- 'Qwen/Qwen-7B-Chat' - 'Qwen/Qwen-7B-Chat'
- 'BAAI/AquilaChat2-7B' - 'BAAI/AquilaChat2-7B'
- '01-ai/Yi-6B' # - '01-ai/Yi-6B'
- 'meta-llama/Llama-2-7b-chat-hf' - 'meta-llama/Llama-2-7b-chat-hf'
- 'meta-llama/Llama-2-13b-chat-hf' - 'meta-llama/Llama-2-13b-chat-hf'
- 'WisdomShell/CodeShell-7B-Chat' - 'WisdomShell/CodeShell-7B-Chat'

2
python/llm/test/benchmark/igpu-perf/1024-128_437.yaml
View file

@ -1,5 +1,7 @@
repo_id: repo_id:
- 'Qwen/Qwen1.5-7B-Chat' - 'Qwen/Qwen1.5-7B-Chat'
- 'meta-llama/Meta-Llama-3-8B-Instruct'
- '01-ai/Yi-6B-Chat'
local_model_hub: 'path to your local model hub' local_model_hub: 'path to your local model hub'
warm_up: 1 warm_up: 1
num_trials: 3 num_trials: 3

2
python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16.yaml
View file

@ -6,7 +6,7 @@ repo_id:
- 'internlm/internlm-chat-7b-8k' - 'internlm/internlm-chat-7b-8k'
- 'Qwen/Qwen-7B-Chat' - 'Qwen/Qwen-7B-Chat'
- 'BAAI/AquilaChat2-7B' - 'BAAI/AquilaChat2-7B'
- '01-ai/Yi-6B' # - '01-ai/Yi-6B'
- 'meta-llama/Llama-2-7b-chat-hf' - 'meta-llama/Llama-2-7b-chat-hf'
- 'meta-llama/Llama-2-13b-chat-hf' - 'meta-llama/Llama-2-13b-chat-hf'
- 'WisdomShell/CodeShell-7B-Chat' - 'WisdomShell/CodeShell-7B-Chat'

2
python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml
View file

@ -1,5 +1,7 @@
repo_id: repo_id:
- 'Qwen/Qwen1.5-7B-Chat' - 'Qwen/Qwen1.5-7B-Chat'
- 'meta-llama/Meta-Llama-3-8B-Instruct'
- '01-ai/Yi-6B-Chat'
local_model_hub: 'path to your local model hub' local_model_hub: 'path to your local model hub'
warm_up: 1 warm_up: 1
num_trials: 3 num_trials: 3

2
python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit.yaml
View file

@ -6,7 +6,7 @@ repo_id:
- 'internlm/internlm-chat-7b-8k' - 'internlm/internlm-chat-7b-8k'
- 'Qwen/Qwen-7B-Chat' - 'Qwen/Qwen-7B-Chat'
- 'BAAI/AquilaChat2-7B' - 'BAAI/AquilaChat2-7B'
- '01-ai/Yi-6B' # - '01-ai/Yi-6B'
- 'meta-llama/Llama-2-7b-chat-hf' - 'meta-llama/Llama-2-7b-chat-hf'
- 'meta-llama/Llama-2-13b-chat-hf' - 'meta-llama/Llama-2-13b-chat-hf'
- 'WisdomShell/CodeShell-7B-Chat' - 'WisdomShell/CodeShell-7B-Chat'

2
python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit_437.yaml
View file

@ -1,5 +1,7 @@
repo_id: repo_id:
- 'Qwen/Qwen1.5-7B-Chat' - 'Qwen/Qwen1.5-7B-Chat'
- 'meta-llama/Meta-Llama-3-8B-Instruct'
- '01-ai/Yi-6B-Chat'
local_model_hub: 'path to your local model hub' local_model_hub: 'path to your local model hub'
warm_up: 1 warm_up: 1
num_trials: 3 num_trials: 3

2
python/llm/test/benchmark/igpu-perf/2048-256.yaml
View file

@ -6,7 +6,7 @@ repo_id:
- 'internlm/internlm-chat-7b-8k' - 'internlm/internlm-chat-7b-8k'
- 'Qwen/Qwen-7B-Chat' - 'Qwen/Qwen-7B-Chat'
- 'BAAI/AquilaChat2-7B' - 'BAAI/AquilaChat2-7B'
- '01-ai/Yi-6B' # - '01-ai/Yi-6B'
- 'meta-llama/Llama-2-7b-chat-hf' - 'meta-llama/Llama-2-7b-chat-hf'
- 'meta-llama/Llama-2-13b-chat-hf' - 'meta-llama/Llama-2-13b-chat-hf'
- 'WisdomShell/CodeShell-7B-Chat' - 'WisdomShell/CodeShell-7B-Chat'

2
python/llm/test/benchmark/igpu-perf/2048-256_437.yaml
View file

@ -1,5 +1,7 @@
repo_id: repo_id:
- 'Qwen/Qwen1.5-7B-Chat' - 'Qwen/Qwen1.5-7B-Chat'
- 'meta-llama/Meta-Llama-3-8B-Instruct'
- '01-ai/Yi-6B-Chat'
local_model_hub: 'path to your local model hub' local_model_hub: 'path to your local model hub'
warm_up: 1 warm_up: 1
num_trials: 3 num_trials: 3

2
python/llm/test/benchmark/igpu-perf/32-32.yaml
View file

@ -6,7 +6,7 @@ repo_id:
- 'internlm/internlm-chat-7b-8k' - 'internlm/internlm-chat-7b-8k'
- 'Qwen/Qwen-7B-Chat' - 'Qwen/Qwen-7B-Chat'
- 'BAAI/AquilaChat2-7B' - 'BAAI/AquilaChat2-7B'
- '01-ai/Yi-6B' # - '01-ai/Yi-6B'
- 'meta-llama/Llama-2-7b-chat-hf' - 'meta-llama/Llama-2-7b-chat-hf'
- 'meta-llama/Llama-2-13b-chat-hf' - 'meta-llama/Llama-2-13b-chat-hf'
- 'WisdomShell/CodeShell-7B-Chat' - 'WisdomShell/CodeShell-7B-Chat'

2
python/llm/test/benchmark/igpu-perf/32-32_437.yaml
View file

@ -1,5 +1,7 @@
repo_id: repo_id:
- 'Qwen/Qwen1.5-7B-Chat' - 'Qwen/Qwen1.5-7B-Chat'
- 'meta-llama/Meta-Llama-3-8B-Instruct'
- '01-ai/Yi-6B-Chat'
local_model_hub: 'path to your local model hub' local_model_hub: 'path to your local model hub'
warm_up: 3 warm_up: 3
num_trials: 5 num_trials: 5