This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
2
Packages
Projects
Releases
Wiki
Activity
Files
1806d1adfc9b598bc6eb94de38a330aaad04c291
vLLM
/
vllm
/
models
/
deepseek_v4
T
History
TJian
1806d1adfc
[ROCm] [DSv4] [Perf] Support DeepSeek v4 MTP (
#43385
)
...
Signed-off-by: tjtanaa <
tunjian.tan@embeddedllm.com
>
2026-05-24 18:43:08 +08:00
..
amd
[ROCm] [DSv4] [Perf] Support DeepSeek v4 MTP (
#43385
)
2026-05-24 18:43:08 +08:00
common
[XPU]fix: add XPU platform guards to DeepSeek-V4 ops (
#42950
)
2026-05-23 06:29:45 +08:00
nvidia
[DSV4] More multi-stream enablement for c4a (
#42925
)
2026-05-23 09:22:27 +08:00
__init__.py
[Model Refactoring] Rename deepseek_v4.py to model.py [4/N] (
#43077
)
2026-05-19 01:12:46 -07:00
compressor.py
[XPU]fix: add XPU platform guards to DeepSeek-V4 ops (
#42950
)
2026-05-23 06:29:45 +08:00
quant_config.py
Add NVFP4 MOE support for Deepseek V4. (
#42209
)
2026-05-22 07:21:51 -07:00