biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Core][Model] PrithviMAE Enablement on vLLM v1 engine (#20577)

Browse Source 
Signed-off-by: Christian Pinto <christian.pinto@ibm.com>
This commit is contained in:
Christian Pinto
2025-07-23 19:00:23 +01:00
committed by GitHub
parent 316b1bf706
commit 8560a5b258
15 changed files with 704 additions and 238 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
vllm/v1/engine/llm_engine.py
View File

@@ -82,11 +82,14 @@ class LLMEngine:
self.dp_group = None
self.should_execute_dummy_batch = False
# Tokenizer (+ ensure liveness if running in another process).
self.tokenizer = init_tokenizer_from_configs(
model_config=vllm_config.model_config,
scheduler_config=vllm_config.scheduler_config,
lora_config=vllm_config.lora_config)
if self.model_config.skip_tokenizer_init:
self.tokenizer = None
else:
# Tokenizer (+ ensure liveness if running in another process).
self.tokenizer = init_tokenizer_from_configs(
model_config=vllm_config.model_config,
scheduler_config=vllm_config.scheduler_config,
lora_config=vllm_config.lora_config)
# Processor (convert Inputs --> EngineCoreRequests)
self.processor = Processor(vllm_config=vllm_config,