Morph MORPH
SIGN IN SIGN UP
dhruvhead / recipes UNCLAIMED
0 0 0 JavaScript

ACTIVITY

Commits Reviews
week month year
COMMITS
13
in the last week
CONTRIBUTORS
7
active
STARS
0
total
FORKS
0
total
TOP CONTRIBUTORS
T
Tiezhen WANG
3 commits
Y
yiminghub2024
3 commits
S
Stefano Castagnetta
2 commits
L
Louie Tsai
2 commits
V
vllmellm
1 commit
T
Thien Tran
1 commit
K
Kyle Sayers
1 commit
RECENT COMMITS
V
[AMD] Verified deepseek-v4-flash recipes on mi300x (#830)
vllmellm
d083490
T
[Model] Add support for GLM 5.3 Flash (#851)
Tiezhen WANG
8bb447d
T
[Skill] Merge recipe authoring and validation workflows (#850)
Tiezhen WANG
c7e36db
T
Add Qwen3.8-Flash-Next recipe (#848)
Thien Tran
8cdf25b
Y
[doc] Qwen3.8-27B Support Native block-scaled FP8 on Ascend 950PR (#847)
yiminghub2024
442f323
S
Qwen3.6-35B-A3B: require vLLM 0.28.0 for the NVFP4 variant (#833)
Stefano Castagnetta
700fcd8
Y
[Doc] Add Ascend 910C 4-node MP support to moonshotai/Kimi-K3 (#842)
yiminghub2024
f657016
K
Add RedHatAI NVFP4-REAP-25 variant to Qwen3.8-2.4T-A95B (#843)
Kyle Sayers
152c5f9
S
Qwen3.6-27B: require vLLM 0.28.0 for the NVFP4 variant (#834)
Stefano Castagnetta
c3cb50c
Y
[Doc] Update Qwen3.8-27B with dflash2 support (#837)
yiminghub2024
e3c120d
L
[Xeon] added Gemma recipes (#823)
Louie Tsai
7c1fdd0
L
[Xeon] Add remining Qwen model recipes (#820)
Louie Tsai
e207b14
T
Update Muse Glimmer nightly and DFlash warmup settings (#835)
Tiezhen WANG
ff37f2f