Commit 984b0e3
committed
qwen-3.5-native sample applicaton based on modeling api and IR format only.
/build/samples/cpp/module_genai/md_qwen3_5_modeling \
--model ~/work/openvino.genai.modular-ws/openvino-new-arch/Qwen3.5-35B-A3B-Base_VL_OV_IR \
--mode text --prompt "how to run Qwen3.5 with pytorch" --device GPU.1
[quant] suffix: _q4a_b4a_g128
[info] Text IR not found; falling back to VL text IR with zero visual inputs: "/home/xzhan34/work/openvino.genai.modular-ws/openvino-new-arch/Qwen3.5-35B-A3B-Base_VL_OV_IR/qwen3_5_text_vl_q4a_b4a_g128.xml"
[load] text IR: "/home/xzhan34/work/openvino.genai.modular-ws/openvino-new-arch/Qwen3.5-35B-A3B-Base_VL_OV_IR/qwen3_5_text_vl_q4a_b4a_g128.xml"
[compile] text -> GPU.1
Failed to infer a tool call example (possible template bug)
Mode: hf / text
Prompt token size: 11
Output token size: 64
TTFT: 3931.08 ms
Decode time: 253332.33 ms
TPOT: 4021.15 ms/token
Throughput: 0.25 tokens/s
It looks like there might be a typo in your request, as the latest official release is **Qwen2.5**.
Signed-off-by: Zhang, Xiaolin <xiaolin.zhang@intel.com>1 parent add8ce5 commit 984b0e3
File tree
58 files changed
+10613
-5
lines changed- cmake
- samples/cpp/module_genai
- comfyui
- src/cpp
- src
- gguf_utils
- modeling
- layers
- models/qwen3_5
- ops
- weights
- tests/cpp
Some content is hidden
Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.
58 files changed
+10613
-5
lines changed| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
66 | 66 | | |
67 | 67 | | |
68 | 68 | | |
| 69 | + | |
| 70 | + | |
| 71 | + | |
| 72 | + | |
| 73 | + | |
| 74 | + | |
69 | 75 | | |
70 | 76 | | |
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
46 | 46 | | |
47 | 47 | | |
48 | 48 | | |
49 | | - | |
| 49 | + | |
| 50 | + | |
| 51 | + | |
| 52 | + | |
| 53 | + | |
| 54 | + | |
| 55 | + | |
| 56 | + | |
| 57 | + | |
| 58 | + | |
| 59 | + | |
| 60 | + | |
| 61 | + | |
| 62 | + | |
| 63 | + | |
| 64 | + | |
| 65 | + | |
| 66 | + | |
| 67 | + | |
| 68 | + | |
| 69 | + | |
| 70 | + | |
| 71 | + | |
| 72 | + | |
| 73 | + | |
| 74 | + | |
| 75 | + | |
| 76 | + | |
| 77 | + | |
| 78 | + | |
| 79 | + | |
| 80 | + | |
| 81 | + | |
| 82 | + | |
| 83 | + | |
| 84 | + | |
| 85 | + | |
| 86 | + | |
| 87 | + | |
| 88 | + | |
| 89 | + | |
| 90 | + | |
| 91 | + | |
| 92 | + | |
| 93 | + | |
| 94 | + | |
| 95 | + | |
| 96 | + | |
| 97 | + | |
| 98 | + | |
| 99 | + | |
| 100 | + | |
| 101 | + | |
| 102 | + | |
| 103 | + | |
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
6 | 6 | | |
7 | 7 | | |
8 | 8 | | |
9 | | - | |
| 9 | + | |
| 10 | + | |
| 11 | + | |
| 12 | + | |
| 13 | + | |
10 | 14 | | |
11 | 15 | | |
12 | 16 | | |
| |||
21 | 25 | | |
22 | 26 | | |
23 | 27 | | |
| 28 | + | |
24 | 29 | | |
25 | 30 | | |
26 | 31 | | |
| |||
0 commit comments