Morph MORPH
SIGN IN SIGN UP
tejas / vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

0 0 122 Python

ACTIVITY

Commits Reviews
week month year
COMMITS
20
in the last year
CONTRIBUTORS
20
active
STARS
0
total
FORKS
0
total
TOP CONTRIBUTORS
B
bhaktatejas922
1 commit
M
Matthew Bonanni
1 commit
C
Cyrus Leung
1 commit
K
Kuntai Du
1 commit
Z
Zhuohan Li
1 commit
J
Jiangyun Zhu
1 commit
Y
Yihua Cheng
1 commit
V
Varun Sundar Rabindranath
1 commit
W
Wentao Ye
1 commit
P
Pengchao Wang
1 commit
RECENT COMMITS
B
qwen3moe on gh200
bhaktatejas922
5a1097c
M
[Attention] Add missing kv cache scale setup (#27490)
Matthew Bonanni
a99564a
C
[Misc] Simplify max tokens in multimodal registry (#27500)
Cyrus Leung
4c5f632
K
[Core][Hybrid allocator + kv connector 1/n] Enable hybrid allocator + KV cache connector (#25712)
Kuntai Du
b853540
Z
Revert "[Misc] Remove use of CUDA_VISIBLE_DEVICES for device selectio… (#27502)
Zhuohan Li
56ed760
J
[CI] Add tests for cudagraph (#27391)
Jiangyun Zhu
29c9cb8
Y
[KVConnector] Migrate the LMCache integration code to be vLLM native (#25542)
Yihua Cheng
83f478b
V
[Misc][DP] Guard mxfp4 implementation selection (#27484)
Varun Sundar Rabindranath
269c4db
W
[Log] Optimize Startup Log (#26740)
Wentao Ye
52efc34
P
[Distributed] Basic set of configuration for large EP deployment on GB200 (#27328)
Pengchao Wang
d95d0f4
L
[Perf][Async Scheduling] Remove CPU->GPU sync in dummy_run (#27455)
Lehua Ding
0402428
J
[Document] Add ms-swift library to rlhf.md (#27469)
jinghanhu
17af6aa
Z
[CI/Build] Fix test_torch_utils in AMD CI (#27317)
Zhewen Li
fc168c3
I
[Bugfix] Fix interns1-vit qk norm code path (#27480)
Isotr0py
acc78ae
M
[Attention] Add MLA prefill backend: trtllm_ragged_attention_deepseek (#26397)
Ming Yang
0f67d4d
K
[Bugfix] Fix MultiConnector stats reconstruction across process boundaries (#27366)
kourosh hakhamaneshi
7e1d697
C
[NIXL][BUGFIX] delay done_recving queue cleanup to bottom of get_finished (#27297)
Chendi.Xue
699d62e
R
[compile] Turn standalone_compile back on (#27460)
Richard Zou
cd390b6
F
[cpu][fix] Fix onednn_mm crash on consecutive matmuls with same M,K,N and different dtype (#27472)
Fadi Arafeh
2080b05
L
[Doc] Fix minor issues in docs/design/metrics.md (#27436)
Lifans
6454afe