xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-08 14:08:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] refactor(config): clean up unused code (#6320)

Browse Source
This commit is contained in:
aniaan 2024-07-11 17:39:07 +08:00 committed by GitHub
parent c4774eb841
commit 3963a5335b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/config.py
View File

@ -138,12 +138,10 @@ class ModelConfig:
self.quantization = quantization
self.quantization_param_path = quantization_param_path
self.enforce_eager = enforce_eager
self.max_context_len_to_capture = max_context_len_to_capture
if self.max_context_len_to_capture is not None:
if max_context_len_to_capture is not None:
raise ValueError("`max_context_len_to_capture` is deprecated. "
"Use `max_seq_len_to_capture` instead.")
self.max_seq_len_to_capture = (max_seq_len_to_capture
or max_context_len_to_capture)
self.max_seq_len_to_capture = max_seq_len_to_capture
self.max_logprobs = max_logprobs
self.disable_sliding_window = disable_sliding_window
self.skip_tokenizer_init = skip_tokenizer_init

3
vllm/worker/xpu_model_runner.py
View File

@ -109,9 +109,6 @@ class XPUModelRunner(ModelRunnerBase[ModelInputForXPU]):
self.kv_cache_dtype = kv_cache_dtype
self.block_size = cache_config.block_size
self.max_context_len_to_capture = (
self.model_config.max_context_len_to_capture
if self.model_config is not None else 0)
self.attn_backend = get_attn_backend(
self.model_config.get_num_attention_heads(self.parallel_config),