From 48b85593b3703a0ff537fdab7623f54cf7dbefb6 Mon Sep 17 00:00:00 2001
From: Yuwen Hu <54161268+Oscilloscope98@users.noreply.github.com>
Date: Thu, 7 Dec 2023 10:32:09 +0800
Subject: [PATCH] Update all-in-one benchmark readme (#9618)

---
 python/llm/dev/benchmark/all-in-one/README.md | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/python/llm/dev/benchmark/all-in-one/README.md b/python/llm/dev/benchmark/all-in-one/README.md
index 06d0b5c3..35734ad4 100644
--- a/python/llm/dev/benchmark/all-in-one/README.md
+++ b/python/llm/dev/benchmark/all-in-one/README.md
@@ -21,10 +21,12 @@ repo_id:
   - 'THUDM/chatglm-6b'
   - 'THUDM/chatglm2-6b'
   - 'meta-llama/Llama-2-7b-chat-hf'
+  # - 'liuhaotian/llava-v1.5-7b' # requires a LLAVA_REPO_DIR env variables pointing to the llava dir; added only for gpu win related test_api now
 local_model_hub: 'path to your local model hub'
 warm_up: 1
 num_trials: 3
 num_beams: 1 # default to greedy search
+low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
 in_out_pairs:
   - '32-32'
   - '1024-128'
@@ -36,6 +38,9 @@ test_api:
   # - "ipex_fp16_gpu" # on Intel GPU
   # - "transformer_int4_gpu"  # on Intel GPU
   # - "optimize_model_gpu"  # on Intel GPU
+  # - "deepspeed_transformer_int4_cpu" # on Intel SPR Server
+  # - "transformer_int4_gpu_win" # on Intel GPU for Windows (catch GPU peak memory)
+cpu_embedding: False # whether put embedding to CPU (only avaiable now for gpu win related test_api)
 ```
 
 ## Run