Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
OpenDAS
vllm_cscc
Repository
Branches
Overview
Active
Stale
All
v0.15.1-dev-pp-mtp-2
6b7cdbf4
·
优化pp+mtp代码
·
May 09, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.15.1-dev
default
protected
ae0539e7
·
Update README.md
·
May 09, 2026
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.15.1-dev-pd_bugfix
02e5f211
·
[PD][Bugfix] 修复影响其他connector的bug
·
May 09, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
step35-mtp3-018
dbcf9f45
·
fix spec_layer_weight_names
·
May 09, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.18.1-dev-kvprune
5c1e8006
·
vllm kvprune for tritonx:v1.1.4
·
May 07, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.15.1-dev-wm-pp-mtp
587c919c
·
[Feat]初步实现PP+MTP
·
May 06, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.15.1-dev-fth
643dc095
·
[feature]w8a8量化模型默认不开启aiter
·
May 06, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.20.0
e8b4d1da
·
[Feature] Support deepgeemm on rocm
·
Apr 30, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.15.1-dev-low-latency-w4a8-marlin
8a74165f
·
w4a8 默认使用deepgemm的masked接口
·
Apr 24, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
wanghl_op_fusion
fc345b74
·
恢复误删代码
·
Apr 23, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.15.1-dev_laibao_tc
624eab7c
·
[BUGFIX] 修复 Qwen3.5 在新版 transformers 下的配置兼容问题并统一 ROCm unified attention 路由
·
Apr 23, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.15_pd_pp_mtp
17b624a0
·
support pp+mtp
·
Apr 23, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.15.1-glm5-w4a8-pd-debug
83750a84
·
[TMP] 临时修改P节点 关于MTP new_token计算
·
Apr 23, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.15.1-dev-aiter-w8a8-lxh
4ee85c63
·
[FEATURE] 接入Aiter MoE W8A8 量化模型支持
·
Apr 22, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.15.1-dev-pcp
43fe650e
·
[FEATURE] 接入Aiter MoE W8A8 量化模型支持
·
Apr 22, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
triton-mla-ver
4238a0cf
·
[fix]新triton与torch2.9.0的适配版本为3.5.1
·
Apr 22, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.11.0-dev
587a5c60
·
[feature] add scaled_fp8_quant_weight for online ptpc_fp8 quant.
·
Apr 22, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.19.1
abdcf7a2
·
[Version] Update vllm 0.19.1
·
Apr 18, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.15.1-dev-lxh-aiter-w8a8
7f74da5a
·
[FEATURE] 接入Aiter MoE W8A8 量化模型支持 && MQA_logits 修改 (Ref:wanghl)
·
Apr 16, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
v0.15.1-dev-lxh
2be9c33c
·
[BUGFIX]解决推测解码内核类型不匹配
·
Apr 15, 2026
Compare
Select Archive Format
Download source code
zip
tar.gz
tar.bz2
tar
Prev
1
2
3
4
5
Next