From 27b4b104ed19081f041840bab80f34ad4a840332 Mon Sep 17 00:00:00 2001 From: Jinhe Date: Thu, 8 Aug 2024 16:42:18 +0800 Subject: [PATCH] Add `qwen2-1.5b-instruct` into igpu performance (#11735) * updated qwen1.5B to all transformer==4.37 yaml * updated qwen1.5B to all transformer==4.37 yaml --- python/llm/test/benchmark/igpu-perf/1024-128_437.yaml | 1 + python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml | 1 + .../benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_437.yaml | 1 + python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_437.yaml | 1 + python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16_437.yaml | 1 + python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_437.yaml | 1 + python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16_437.yaml | 1 + 7 files changed, 7 insertions(+) diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_437.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_437.yaml index f191801c..b87e6c2c 100644 --- a/python/llm/test/benchmark/igpu-perf/1024-128_437.yaml +++ b/python/llm/test/benchmark/igpu-perf/1024-128_437.yaml @@ -1,5 +1,6 @@ repo_id: - 'Qwen/Qwen1.5-7B-Chat' + - 'Qwen/Qwen2-1.5B-Instruct' - 'Qwen/Qwen2-7B-Instruct' - 'microsoft/Phi-3-mini-4k-instruct' - 'microsoft/Phi-3-mini-128k-instruct' diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml index f9db9131..d7172186 100644 --- a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml +++ b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml @@ -1,5 +1,6 @@ repo_id: - 'Qwen/Qwen1.5-7B-Chat' + - 'Qwen/Qwen2-1.5B-Instruct' - 'Qwen/Qwen2-7B-Instruct' - 'microsoft/Phi-3-mini-4k-instruct' - 'microsoft/Phi-3-mini-128k-instruct' diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_437.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_437.yaml index abd17aaa..3839d0d2 100644 --- a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_437.yaml +++ b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_437.yaml @@ -1,5 +1,6 @@ repo_id: - 'Qwen/Qwen1.5-7B-Chat' + - 'Qwen/Qwen2-1.5B-Instruct' - 'Qwen/Qwen2-7B-Instruct' - 'microsoft/Phi-3-mini-4k-instruct' - 'microsoft/Phi-3-mini-128k-instruct' diff --git a/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_437.yaml b/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_437.yaml index fd4fbbfa..d6ee670e 100644 --- a/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_437.yaml +++ b/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_437.yaml @@ -1,5 +1,6 @@ repo_id: - 'Qwen/Qwen1.5-7B-Chat' + - 'Qwen/Qwen2-1.5B-Instruct' - 'Qwen/Qwen2-7B-Instruct' - 'microsoft/Phi-3-mini-4k-instruct' - 'microsoft/Phi-3-mini-128k-instruct' diff --git a/python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16_437.yaml b/python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16_437.yaml index cfd7cc31..ddbf1cf4 100644 --- a/python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16_437.yaml +++ b/python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16_437.yaml @@ -1,5 +1,6 @@ repo_id: - 'Qwen/Qwen1.5-7B-Chat' + - 'Qwen/Qwen2-1.5B-Instruct' - 'Qwen/Qwen2-7B-Instruct' - 'microsoft/Phi-3-mini-4k-instruct' - 'microsoft/Phi-3-mini-128k-instruct' diff --git a/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_437.yaml b/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_437.yaml index 93fdc926..1a969165 100644 --- a/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_437.yaml +++ b/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_437.yaml @@ -1,5 +1,6 @@ repo_id: - 'Qwen/Qwen1.5-7B-Chat' + - 'Qwen/Qwen2-1.5B-Instruct' - 'Qwen/Qwen2-7B-Instruct' - 'microsoft/Phi-3-mini-4k-instruct' - 'microsoft/Phi-3-mini-128k-instruct' diff --git a/python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16_437.yaml b/python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16_437.yaml index 7c2632d3..c85da867 100644 --- a/python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16_437.yaml +++ b/python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16_437.yaml @@ -1,5 +1,6 @@ repo_id: - 'Qwen/Qwen1.5-7B-Chat' + - 'Qwen/Qwen2-1.5B-Instruct' - 'Qwen/Qwen2-7B-Instruct' - 'microsoft/Phi-3-mini-4k-instruct' - 'microsoft/Phi-3-mini-128k-instruct'