kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-13 14:07:21 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][doc] Update Qwen3-Next doc by adding known issues section (#10582)

Browse Source 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
This commit is contained in:
Guoming Zhang 2026-01-11 14:47:47 +08:00 committed by GitHub
parent b2e2538fcd
commit 0371cbfd88
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/source/deployment-guide/deployment-guide-for-qwen3-next-on-trtllm.md
View File

@ -227,3 +227,7 @@ Run `bench.sh` to begin a serving benchmark. This will take a long time if you r
```shell
./bench.sh
```
## Known Issues
Qwen3-Next-80B-A3B exhibits relatively low accuracy on the SciCode-AA-v2 benchmark.

7
docs/source/models/supported-models.md
View File

@ -38,13 +38,14 @@ Note: Support for other models may vary. Features marked "N/A" are not applicabl
| `DeepseekV3ForCausalLM` | Yes | Yes | Yes | Yes | Yes [^1] | Yes | No | No | Yes | Yes | Yes [^2] | N/A | Yes | Yes |
| `DeepseekV32ForCausalLM` | Yes | Yes | Yes | Yes | Yes | Yes | No | No | Yes | Yes | Yes | N/A | Yes | Yes |
| `Qwen3MoeForCausalLM` | Yes | Yes | Yes | Yes | Yes | No | Yes | Yes | Yes | Yes | Yes | N/A | Yes | Yes |
| `Qwen3NextForCausalLM` | Yes | Yes | No | Untested | Yes | No | No | No | Yes | Yes | No | No | Untested | Untested |
| `Qwen3NextForCausalLM` [^3] | Yes | Yes | No | Untested | Yes | No | No | No | Yes | Yes | No | No | Untested | Untested |
| `Llama4ForConditionalGeneration` | Yes | Yes | Yes | Yes | Yes | No | Yes | Yes | Yes | Yes | Untested | N/A | Yes | Yes |
| `GptOssForCausalLM` | Yes | Yes | Yes | Yes | Yes | No | Yes | Yes [^3] | Yes | Yes | Yes | N/A | Yes | Yes |
| `GptOssForCausalLM` | Yes | Yes | Yes | Yes | Yes | No | Yes | Yes [^4] | Yes | Yes | Yes | N/A | Yes | Yes |
[^1]: Chunked Prefill for MLA can only be enabled on SM100/SM103.
[^2]: KV cache reuse for MLA can only be enabled on SM90/SM100/SM103 and in BF16/FP8 KV cache dtype.
[^3]: Overlap scheduler isn't supported when using EAGLE-3(Two Model Engine) for GPT-OSS.
[^3]: Qwen3-Next-80B-A3B exhibits relatively low accuracy on the SciCode-AA-v2 benchmark.
[^4]: Overlap scheduler isn't supported when using EAGLE-3(Two Model Engine) for GPT-OSS.
# Multimodal Feature Support Matrix (PyTorch Backend)