change self.get_tokenizer_for_seq to get_tokenizer_for_seq

CMakeLists.txt

@@ -150,7 +150,7 @@ set(VLLM_EXT_SRC
   "csrc/layernorm_kernels.cu"
   "csrc/transpose_kernels.cu"
   "csrc/quantization/squeezellm/quant_cuda_kernel.cu"
-  "csrc/quantization/gptq/q_gemm.cu"
+  # "csrc/quantization/gptq/q_gemm.cu"
   "csrc/quantization/compressed_tensors/int8_quant_kernels.cu"
   # "csrc/quantization/fp8/common.cu"
   "csrc/cuda_utils_kernels.cu"

vllm/engine/llm_engine.py

@@ -354,10 +354,10 @@ class LLMEngine:
                     self.detokenizer,
                     self.scheduler,
                     self.seq_counter,
-                    self.get_tokenizer_for_seq,
+                    get_tokenizer_for_seq,
                     stop_checker=StopChecker(
                         self.scheduler_config.max_model_len,
-                        self.get_tokenizer_for_seq,
+                        get_tokenizer_for_seq,
                     ),
                 ))
             init_success = True