A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 12, 13:30 UTC
Fix TeleChatForCausalLM not register issue (#29473)
Signed-off-by: Lai, Yejing <yejing.lai@intel.com>
Yejing Lai committed
Nov 26, 2025 at 21:15 UTC
bb706d60482233e2feb6bab894492e394dcdef94
2 files changed
+5
tests/models/registry.py
+3
@@ -436,6 +436,9 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
436
"SolarForCausalLM": _HfExamplesInfo(
437
"upstage/solar-pro-preview-instruct", trust_remote_code=True
438
),
439
+ "TeleChatForCausalLM": _HfExamplesInfo(
440
+ "chuhac/TeleChat2-35B", trust_remote_code=True
441
+ ),
442
"TeleChat2ForCausalLM": _HfExamplesInfo(
443
"Tele-AI/TeleChat2-3B", trust_remote_code=True
444
),
vllm/model_executor/models/registry.py
+2
@@ -170,6 +170,7 @@ _TEXT_GENERATION_MODELS = {
170
"StableLmForCausalLM": ("stablelm", "StablelmForCausalLM"),
171
"Starcoder2ForCausalLM": ("starcoder2", "Starcoder2ForCausalLM"),
172
"SolarForCausalLM": ("solar", "SolarForCausalLM"),
173
+ "TeleChatForCausalLM": ("telechat2", "TeleChat2ForCausalLM"),
174
"TeleChat2ForCausalLM": ("telechat2", "TeleChat2ForCausalLM"),
175
"TeleFLMForCausalLM": ("teleflm", "TeleFLMForCausalLM"),
176
"XverseForCausalLM": ("llama", "LlamaForCausalLM"),
@@ -207,6 +208,7 @@ _EMBEDDING_MODELS = {
208
"Qwen2ForProcessRewardModel": ("qwen2_rm", "Qwen2ForProcessRewardModel"),
209
"RobertaForMaskedLM": ("roberta", "RobertaEmbeddingModel"),
210
"RobertaModel": ("roberta", "RobertaEmbeddingModel"),
211
+ "TeleChatForCausalLM": ("telechat2", "TeleChat2ForCausalLM"),
212
"TeleChat2ForCausalLM": ("telechat2", "TeleChat2ForCausalLM"),
213
"XLMRobertaModel": ("roberta", "RobertaEmbeddingModel"),
214
# [Multimodal]