xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 06:35:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

[BugFix] Fix failing test quantization/test_compressed_tensors.py::test_compressed_tensors_fp8_block_enabled (#26436)

Browse Source 
Signed-off-by: morrison-turnansky <mturnans@redhat.com>
This commit is contained in:
Morrison Turnansky 2025-10-08 16:04:12 -04:00 committed by GitHub
parent b82f4307c9
commit e1ba235668
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/config/vllm.py
View File

@ -597,7 +597,7 @@ class VllmConfig:
# https://github.com/vllm-project/vllm/issues/25094 # https://github.com/vllm-project/vllm/issues/25094
if has_blocked_weights(): if has_blocked_weights():
custom_ops = self.compilation_config.custom_ops custom_ops = self.compilation_config.custom_ops
if "none" not in custom_ops and "-quant_fp8" not in custom_ops: if "-quant_fp8" not in custom_ops:
custom_ops.append("+quant_fp8") custom_ops.append("+quant_fp8")
def update_sizes_for_sequence_parallelism(self, possible_sizes: list) -> list: def update_sizes_for_sequence_parallelism(self, possible_sizes: list) -> list: