From a79dfc108cad40f99ade60c091b55f4b990ef98e Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Tue, 23 Dec 2025 12:10:17 +0000 Subject: [PATCH] =?UTF-8?q?=E4=BF=AE=E5=A4=8D=E6=9B=B4=E5=A4=9A=E9=94=99?= =?UTF-8?q?=E8=AF=AF=E6=97=A5=E5=BF=97=E4=B8=AD=E7=9A=84=E8=AF=AD=E6=B3=95?= =?UTF-8?q?=E5=92=8C=E6=8B=BC=E5=86=99=E9=97=AE=E9=A2=98?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com> --- fastdeploy/cache_manager/cache_messager.py | 2 +- fastdeploy/engine/common_engine.py | 2 +- fastdeploy/engine/engine.py | 2 +- fastdeploy/engine/sampling_params.py | 2 +- fastdeploy/scheduler/splitwise_scheduler.py | 2 +- fastdeploy/worker/gcu_model_runner.py | 6 +++--- 6 files changed, 8 insertions(+), 8 deletions(-) diff --git a/fastdeploy/cache_manager/cache_messager.py b/fastdeploy/cache_manager/cache_messager.py index 186c67df2..0acd67972 100644 --- a/fastdeploy/cache_manager/cache_messager.py +++ b/fastdeploy/cache_manager/cache_messager.py @@ -603,7 +603,7 @@ class CacheMessagerV1: else: time.sleep(0.001) except Exception as e: - logger.info(f"add cache task occured error: {e}, {traceback.format_exc()!s}.") + logger.info(f"add cache task occurred error: {e}, {traceback.format_exc()!s}.") def prefill_layerwise_send_cache_thread(self): """ diff --git a/fastdeploy/engine/common_engine.py b/fastdeploy/engine/common_engine.py index 99ec5e846..9d74a3699 100644 --- a/fastdeploy/engine/common_engine.py +++ b/fastdeploy/engine/common_engine.py @@ -1641,7 +1641,7 @@ class EngineService: if think_end_id > 0: self.llm_logger.info(f"Get think_end_id {think_end_id} from vocab.") else: - self.llm_logger.info("No token found in vocabulary, the model can not do reasoning.") + self.llm_logger.info("No token found in vocabulary, the model cannot do reasoning.") image_patch_id = self.data_processor.tokenizer.get_vocab().get("<|IMAGE_PLACEHOLDER|>", -1) line_break_id = self.data_processor.tokenizer.get_vocab().get("\n", -1) diff --git a/fastdeploy/engine/engine.py b/fastdeploy/engine/engine.py index 43eb18e47..3c260562e 100644 --- a/fastdeploy/engine/engine.py +++ b/fastdeploy/engine/engine.py @@ -522,7 +522,7 @@ class LLMEngine: if think_end_id > 0: llm_logger.info(f"Get think_end_id {think_end_id} from vocab.") else: - llm_logger.info("No token found in vocabulary, the model can not do reasoning.") + llm_logger.info("No token found in vocabulary, the model cannot do reasoning.") image_patch_id = self.data_processor.tokenizer.get_vocab().get("<|IMAGE_PLACEHOLDER|>", -1) line_break_id = self.data_processor.tokenizer.get_vocab().get("\n", -1) diff --git a/fastdeploy/engine/sampling_params.py b/fastdeploy/engine/sampling_params.py index 908ba6521..e92b37011 100644 --- a/fastdeploy/engine/sampling_params.py +++ b/fastdeploy/engine/sampling_params.py @@ -213,7 +213,7 @@ class SamplingParams: if self.logprobs is not None and (self.logprobs < 0 or self.logprobs > 20): raise ValueError("Invalid value for 'top_logprobs': must be between 0 and 20.") if self.prompt_logprobs is not None: - raise ValueError("prompt_logprobs is not support when FD_USE_GET_SAVE_OUTPUT_V1 is disabled.") + raise ValueError("prompt_logprobs is not supported when FD_USE_GET_SAVE_OUTPUT_V1 is disabled.") else: # True (1) if self.logprobs is not None and self.logprobs < -1: raise ValueError(f"logprobs must be a non-negative value or -1, got {self.logprobs}.") diff --git a/fastdeploy/scheduler/splitwise_scheduler.py b/fastdeploy/scheduler/splitwise_scheduler.py index 106477e14..d47e99507 100644 --- a/fastdeploy/scheduler/splitwise_scheduler.py +++ b/fastdeploy/scheduler/splitwise_scheduler.py @@ -416,7 +416,7 @@ class ResultReader: result = RequestOutput.from_dict(data) self.data.appendleft(result) except Exception as e: - logger.error(f"Parse Result Error:{e}, {str(traceback.format_exc())}, {result}") + logger.error(f"Parse Result Error: {e}, {str(traceback.format_exc())}, {result}") return total diff --git a/fastdeploy/worker/gcu_model_runner.py b/fastdeploy/worker/gcu_model_runner.py index 752bcd340..4754a5a29 100644 --- a/fastdeploy/worker/gcu_model_runner.py +++ b/fastdeploy/worker/gcu_model_runner.py @@ -119,9 +119,9 @@ class GCUModelRunner(ModelRunnerBase): Init speculative proposer """ if self.speculative_method == "ngram": - raise NotImplementedError("NgramProposer is not support by GCUModelRunner.") + raise NotImplementedError("NgramProposer is not supported by GCUModelRunner.") elif self.speculative_method == "mtp": - raise NotImplementedError("MTPProposer is not support by GCUModelRunner.") + raise NotImplementedError("MTPProposer is not supported by GCUModelRunner.") else: self.proposer = None @@ -644,7 +644,7 @@ class GCUModelRunner(ModelRunnerBase): if not profile and ( self.cache_config.enable_prefix_caching or self.scheduler_config.splitwise_role != "mixed" ): - raise NotImplementedError("prefix_caching is not support by GCUModelRunner.") + raise NotImplementedError("prefix_caching is not supported by GCUModelRunner.") else: for i in range(self.model_config.num_hidden_layers):