minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

GLM-5.3-Flash support (#36507)

Browse Source 
Co-authored-by: zRzRzRzRzRzRzR <Yuxuan.Zhang2@liverpool.ac.uk>
Co-authored-by: Shijin Zhang <75300765+Dovis01@users.noreply.github.com>
Co-authored-by: zanes-ops <zanes@nvidia.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Jian Chen <jianchen0311@gmail.com>
Co-authored-by: zijiexia <37504505+zijiexia@users.noreply.github.com>
Co-authored-by: andyluo7 <43718156+andyluo7@users.noreply.github.com>
Co-authored-by: Ehsan Akhgari <ehsan.akhgari@gmail.com>
Co-authored-by: kpham-sgl <khoa.pham@radixark.ai>
Co-authored-by: BBuf <1182563586@qq.com>
Co-authored-by: Raiden Makoto <81530826+Raiden-Makoto@users.noreply.github.com>
This commit is contained in:
Xinyuan Tong
2026-09-06 02:27:59 -07:00
committed by GitHub
co-authored by zRzRzRzRzRzRzR Shijin Zhang zanes-ops Baizhou Zhang Jian Chen zijiexia andyluo7 Ehsan Akhgari kpham-sgl BBuf Raiden Makoto
parent a9944aec01
commit 97c6978369
103 changed files with 7741 additions and 559 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/unit/mem_cache/test_retraction_mamba_backup.py
+4 -2
View File
@@ -30,10 +30,12 @@ class _Allocator:
def get_kvcache(self):
return self._kv
def get_cpu_copy(self, indices, mamba_indices=None):
def get_cpu_copy(self, indices, mamba_indices=None, req_pool_index=None):
return "kv"
def load_cpu_copy(self, cpu_tensors, indices, mamba_indices=None):
def load_cpu_copy(
self, cpu_tensors, indices, mamba_indices=None, req_pool_index=None
):
self.loaded_kv = cpu_tensors