mlc-ai
/

QwQ-32B-q4f32_1-MLC

Model card Files Files and versions Community

ruihanglai commited on 4 days ago

Commit

3023813

·

verified ·

1 Parent(s): 427b372

Update mlc-chat-config.json

Files changed (1) hide show

mlc-chat-config.json +2 -2

mlc-chat-config.json CHANGED Viewed

@@ -14,7 +14,7 @@
     "vocab_size": 152064,
     "tie_word_embeddings": false,
     "context_window_size": 131072,
-    "prefill_chunk_size": 8192,
     "tensor_parallel_shards": 1,
     "head_dim": 128,
     "dtype": "float32",
@@ -23,7 +23,7 @@
   "vocab_size": 152064,
   "context_window_size": 131072,
   "sliding_window_size": -1,
-  "prefill_chunk_size": 8192,
   "attention_sink_size": -1,
   "tensor_parallel_shards": 1,
   "pipeline_parallel_stages": 1,

     "vocab_size": 152064,
     "tie_word_embeddings": false,
     "context_window_size": 131072,
+    "prefill_chunk_size": 2048,
     "tensor_parallel_shards": 1,
     "head_dim": 128,
     "dtype": "float32",
   "vocab_size": 152064,
   "context_window_size": 131072,
   "sliding_window_size": -1,
+  "prefill_chunk_size": 2048,
   "attention_sink_size": -1,
   "tensor_parallel_shards": 1,
   "pipeline_parallel_stages": 1,