Lil2J commited on
Commit
014c9e9
·
verified ·
1 Parent(s): 05579e6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -11,6 +11,8 @@ After implementing Eagle3, the inference performance of Qwen3-30B-Moe using the
11
 
12
  The TPS (tokens per second) improvement reached nearly 70%.
13
 
 
 
14
 
15
  | model | gpu | tps |
16
  |---------|---------|---------|
@@ -18,7 +20,8 @@ The TPS (tokens per second) improvement reached nearly 70%.
18
  | qwen3-30b-moe_eagle3 | h200 | 231 |
19
  | qwen3-30b_moe | 8*h200 | 183 |
20
  | qwen3-30b_moe-eagle3 | 8*h200 | 325 |
21
-
 
22
  ## How to use
23
 
24
  To use Eagle3 with SGLang, first replace the qwen3_moe.py file in SGLang’s directory (sglang/python/sglang/srt/models/) with the qwen3_moe.py file from this project.
 
11
 
12
  The TPS (tokens per second) improvement reached nearly 70%.
13
 
14
+ On a single RTX 5090, the TPS (transactions per second) of Qwen3-8B-Eagle3 increased from 164 to 268.
15
+
16
 
17
  | model | gpu | tps |
18
  |---------|---------|---------|
 
20
  | qwen3-30b-moe_eagle3 | h200 | 231 |
21
  | qwen3-30b_moe | 8*h200 | 183 |
22
  | qwen3-30b_moe-eagle3 | 8*h200 | 325 |
23
+ | qwen3-30b_moe | 8*5090 | 164 |
24
+ | qwen3-30b_moe-eagle3 | 8*5090 | 268 |
25
  ## How to use
26
 
27
  To use Eagle3 with SGLang, first replace the qwen3_moe.py file in SGLang’s directory (sglang/python/sglang/srt/models/) with the qwen3_moe.py file from this project.