diff --git a/docs/models/supported_models.md b/docs/models/supported_models.md index 31a550b95f..21e801a423 100644 --- a/docs/models/supported_models.md +++ b/docs/models/supported_models.md @@ -488,7 +488,6 @@ th { | `TeleChat2ForCausalLM` | TeleChat2 | `Tele-AI/TeleChat2-3B`, `Tele-AI/TeleChat2-7B`, `Tele-AI/TeleChat2-35B`, etc. | ✅︎ | ✅︎ | | `TeleChat3ForCausalLM` | TeleChat3 | `Tele-AI/TeleChat3-36B-Thinking`, `Tele-AI/TeleChat3-Coder-36B-Thinking`, etc. | ✅︎ | ✅︎ | | `TeleFLMForCausalLM` | TeleFLM | `CofeAI/FLM-2-52B-Instruct-2407`, `CofeAI/Tele-FLM`, etc. | ✅︎ | ✅︎ | -| `XverseForCausalLM` | XVERSE | `xverse/XVERSE-7B-Chat`, `xverse/XVERSE-13B-Chat`, `xverse/XVERSE-65B-Chat`, etc. | ✅︎ | ✅︎ | | `MiniMaxM1ForCausalLM` | MiniMax-Text | `MiniMaxAI/MiniMax-M1-40k`, `MiniMaxAI/MiniMax-M1-80k`, etc. | | | | `MiniMaxText01ForCausalLM` | MiniMax-Text | `MiniMaxAI/MiniMax-Text-01`, etc. | | | | `Zamba2ForCausalLM` | Zamba2 | `Zyphra/Zamba2-7B-instruct`, `Zyphra/Zamba2-2.7B-instruct`, `Zyphra/Zamba2-1.2B-instruct`, etc. | | | diff --git a/tests/distributed/test_pipeline_parallel.py b/tests/distributed/test_pipeline_parallel.py index 8530740320..d1196b8e0d 100644 --- a/tests/distributed/test_pipeline_parallel.py +++ b/tests/distributed/test_pipeline_parallel.py @@ -155,9 +155,6 @@ TEXT_GENERATION_MODELS = { "stabilityai/stablelm-3b-4e1t": PPTestSettings.fast(), "bigcode/starcoder2-3b": PPTestSettings.fast(), "upstage/solar-pro-preview-instruct": PPTestSettings.fast(load_format="dummy"), - # FIXME: Cannot load tokenizer in latest transformers version. - # Need to use tokenizer from `meta-llama/Llama-2-7b-chat-hf` - # "xverse/XVERSE-7B-Chat": PPTestSettings.fast(), # [Encoder-only] # TODO: Implement PP # "facebook/bart-base": PPTestSettings.fast(), diff --git a/tests/models/registry.py b/tests/models/registry.py index ac3282e368..f5431e799e 100644 --- a/tests/models/registry.py +++ b/tests/models/registry.py @@ -564,16 +564,6 @@ _TEXT_GENERATION_EXAMPLE_MODELS = { "TeleFLMForCausalLM": _HfExamplesInfo( "CofeAI/FLM-2-52B-Instruct-2407", trust_remote_code=True ), - "XverseForCausalLM": _HfExamplesInfo( - "xverse/XVERSE-7B-Chat", - tokenizer="meta-llama/Llama-2-7b", - trust_remote_code=True, - max_transformers_version="4.57", - transformers_version_reason={ - "vllm": "XVERSE tokenizer is incompatible with transformers v5 " - "(add_prefix_space / prepend_scheme mismatch).", - }, - ), "Zamba2ForCausalLM": _HfExamplesInfo("Zyphra/Zamba2-7B-instruct"), "MiMoForCausalLM": _HfExamplesInfo("XiaomiMiMo/MiMo-7B-RL", trust_remote_code=True), "MiMoV2FlashForCausalLM": _HfExamplesInfo( diff --git a/vllm/model_executor/models/registry.py b/vllm/model_executor/models/registry.py index ecdbe3991c..6c197ad3c5 100644 --- a/vllm/model_executor/models/registry.py +++ b/vllm/model_executor/models/registry.py @@ -214,7 +214,6 @@ _TEXT_GENERATION_MODELS = { "TeleChat2ForCausalLM": ("telechat2", "TeleChat2ForCausalLM"), "TeleChat3ForCausalLM": ("llama", "LlamaForCausalLM"), "TeleFLMForCausalLM": ("teleflm", "TeleFLMForCausalLM"), - "XverseForCausalLM": ("llama", "LlamaForCausalLM"), "Zamba2ForCausalLM": ("zamba2", "Zamba2ForCausalLM"), } @@ -723,6 +722,7 @@ _PREVIOUSLY_SUPPORTED_MODELS = { # have been removed for V0 deprecation. "DonutForConditionalGeneration": "0.10.2", "MllamaForConditionalGeneration": "0.10.2", + "XverseForCausalLM": "0.23.0", } _OOT_SUPPORTED_MODELS = {