File tree Expand file tree Collapse file tree 1 file changed +2
-0
lines changed
Expand file tree Collapse file tree 1 file changed +2
-0
lines changed Original file line number Diff line number Diff line change @@ -8,6 +8,7 @@ The following is a table of supported models for the PyTorch backend:
88| ` BertForSequenceClassification ` | BERT-based | ` textattack/bert-base-uncased-yelp-polarity ` |
99| ` DeciLMForCausalLM ` | Nemotron | ` nvidia/Llama-3_1-Nemotron-51B-Instruct ` |
1010| ` DeepseekV3ForCausalLM ` | DeepSeek-V3 | ` deepseek-ai/DeepSeek-V3 ` |
11+ | ` DeepseekV32ForCausalLM ` | DeepSeek-V3.2 | ` deepseek-ai/DeepSeek-V3.2 ` |
1112| ` Exaone4ForCausalLM ` | EXAONE 4.0 | ` LGAI-EXAONE/EXAONE-4.0-32B ` |
1213| ` Gemma3ForCausalLM ` | Gemma 3 | ` google/gemma-3-1b-it ` |
1314| ` GptOssForCausalLM ` | GPT-OSS | ` openai/gpt-oss-120b ` |
@@ -34,6 +35,7 @@ Note: Support for other models may vary. Features marked "N/A" are not applicabl
3435| Model Architecture/Feature | Overlap Scheduler | CUDA Graph | Attention Data Parallelism | Disaggregated Serving | Chunked Prefill | MTP | EAGLE-3(One Model Engine) | EAGLE-3(Two Model Engine) | Torch Sampler | TLLM C++ Sampler | KV Cache Reuse | Sliding Window Attention | Logits Post Processor | Guided Decoding |
3536| ------------------------------ | ----------------- | ---------- | -------------------------- | --------------------- | --------------- | --- | ------------------------- | ------------------------- | ------------- | ---------------- | -------------- | ------------------------ | --------------------- | --------------- |
3637| ` DeepseekV3ForCausalLM ` | Yes | Yes | Yes | Yes | Yes [ ^ 1 ] | Yes | No | No | Yes | Yes | Yes [ ^ 2 ] | N/A | Yes | Yes |
38+ | ` DeepseekV32ForCausalLM ` | Yes | Yes | Yes | Yes | Yes | Yes | No | No | Yes | Yes | Yes | N/A | Yes | Yes |
3739| ` Qwen3MoeForCausalLM ` | Yes | Yes | Yes | Yes | Yes | No | Yes | Yes | Yes | Yes | Yes | N/A | Yes | Yes |
3840| ` Qwen3NextForCausalLM ` | Yes | Yes | No | Untested | Yes | No | No | No | Yes | Yes | No | No | Untested | Untested |
3941| ` Llama4ForConditionalGeneration ` | Yes | Yes | Yes | Yes | Yes | No | Yes | Yes | Yes | Yes | Untested | N/A | Yes | Yes |
You can’t perform that action at this time.
0 commit comments