[Model] add GLM-5.3-Flash support (#53906)
This commit is contained in:
@@ -120,6 +120,7 @@ _TEXT_GENERATION_MODELS = {
|
||||
"Glm4MoeForCausalLM": ("glm4_moe", "Glm4MoeForCausalLM"),
|
||||
"Glm4MoeLiteForCausalLM": ("glm4_moe_lite", "Glm4MoeLiteForCausalLM"),
|
||||
"GlmMoeDsaForCausalLM": ("vllm.models.deepseek_v32", "GlmMoeDsaForCausalLM"),
|
||||
"Glm5NextForCausalLM": ("vllm.models.glm5next", "Glm5NextForCausalLM"),
|
||||
"GptOssForCausalLM": ("gpt_oss", "GptOssForCausalLM"),
|
||||
"GPT2LMHeadModel": ("gpt2", "GPT2LMHeadModel"),
|
||||
"GPTJForCausalLM": ("gpt_j", "GPTJForCausalLM"),
|
||||
@@ -413,6 +414,10 @@ _MULTIMODAL_MODELS = {
|
||||
"Glm4vForConditionalGeneration": ("glm4_1v", "Glm4vForConditionalGeneration"),
|
||||
"Glm4vMoeForConditionalGeneration": ("glm4_1v", "Glm4vMoeForConditionalGeneration"),
|
||||
"GlmOcrForConditionalGeneration": ("glm_ocr", "GlmOcrForConditionalGeneration"),
|
||||
"Glm5NextForConditionalGeneration": (
|
||||
"vllm.models.glm5next",
|
||||
"Glm5NextForConditionalGeneration",
|
||||
),
|
||||
"GraniteSpeechForConditionalGeneration": (
|
||||
"granite_speech",
|
||||
"GraniteSpeechForConditionalGeneration",
|
||||
@@ -666,6 +671,7 @@ _SPECULATIVE_DECODING_MODELS = {
|
||||
"Glm4MoeMTPModel": ("glm4_moe_mtp", "Glm4MoeMTP"),
|
||||
"Glm4MoeLiteMTPModel": ("glm4_moe_lite_mtp", "Glm4MoeLiteMTP"),
|
||||
"GlmOcrMTPModel": ("glm_ocr_mtp", "GlmOcrMTP"),
|
||||
"Glm5NextMTPModel": ("vllm.models.glm5next", "Glm5NextMTP"),
|
||||
"MedusaModel": ("medusa", "Medusa"),
|
||||
"OpenPanguMTPModel": ("openpangu_mtp", "OpenPanguMTP"),
|
||||
"Qwen3NextMTP": ("qwen3_next_mtp", "Qwen3NextMTP"),
|
||||
|
||||
Reference in New Issue
Block a user