A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 06:45 UTC
config parser: add ChatGLM2 seq_length to `_get_and_verify_max_len` (#1617)
Sin committed
Nov 10, 2023 at 11:29 UTC
0d578228ca220c120bb73316c1d35d078a5bd7b1
1 file changed
+2
vllm/config.py
+2
@@ -368,6 +368,8 @@ def _get_and_verify_max_len(
368
"n_positions",
369
# MPT
370
"max_seq_len",
371
+ # ChatGLM2
372
+ "seq_length",
373
# Others
374
"max_sequence_length",
375
"max_seq_length",