Harry Mellor
cf3eacfe58
Standardise get_rope to use rope_parameters["partial_rotary_factor"], not rotary_dim ( #30389 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-12-11 20:45:23 +00:00
Matthew Bonanni
430dd4d9eb
[Attention] Remove imports from vllm/attention/__init__.py ( #29342 )
...
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2025-11-26 10:53:15 -07:00
Harry Mellor
a8b70304d6
Update rope_scaling to rope_parameters in preparation for Transformers v5 ( #28542 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-11-19 09:06:36 -08:00
Harry Mellor
97d1c99302
Rename clashing method names for vLLM model protocol ( #27583 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-11-12 19:14:33 -08:00
Ilya Markov
e50c454672
[BugFix] Support EP/DP + EPLB with MTP ( #25311 )
...
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
2025-11-05 15:22:17 +00:00
CSWYF3634076
63b22e0dbb
[Model][Bugfix] fix ernie45 moe 300B SharedFusedMoE output tuple ( #27316 )
...
Signed-off-by: wangyafeng <wangyafeng@baidu.com>
2025-10-26 20:53:31 -07:00
CSWYF3634076
01ad27faff
[Model][Bugfix]fix ernie45 load failed due to ernie45 eplb code ( #26684 )
...
Signed-off-by: wangyafeng <wangyafeng@baidu.com>
2025-10-14 06:55:23 +00:00
Harry Mellor
8fcaaf6a16
Update Optional[x] -> x | None and Union[x, y] to x | y ( #26633 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-12 09:51:31 -07:00
Haisheng Chen
c5c8f5ea59
[EPLB] Support ernie4.5-moe ( #22100 )
...
Signed-off-by: Haisheng Chen <langzs335@outlook.com>
Signed-off-by: Haisheng Chen <60504847+HsChen-sys@users.noreply.github.com>
Signed-off-by: Haisheng Chen <hac048@ucsd.edu>
Co-authored-by: Haisheng Chen <langzs335@outlook.com>
2025-10-12 10:40:47 +08:00
bnellnm
47e66c24e2
[Model] Apply shared experts overlap optimization to all models with shared experts ( #26145 )
...
Signed-off-by: Bill Nell <bnell@redhat.com>
2025-10-09 11:31:04 -04:00
Harry Mellor
d6953beb91
Convert formatting to use ruff instead of yapf + isort ( #26247 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-05 07:06:22 -07:00
CSWYF3634076
ef6e0e7132
[Bugfix][Model]fix ernie45 moe gate&bias dtype to float32 ( #25936 )
...
Signed-off-by: wangyafeng <wangyafeng@baidu.com>
2025-09-30 19:11:21 +08:00
Woosuk Kwon
1c3ffdbecc
[V0 Deprecation] Remove V0 sampling metadata ( #25345 )
...
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
2025-09-21 10:37:11 -07:00
whx
4a9375fe9d
[Model] Pass param prefix to LLMHead ( #24862 )
...
Signed-off-by: whx-sjtu <2952154980@qq.com>
2025-09-17 16:01:27 +08:00
Lukas Geiger
de533ab2a1
[Models] Improve iteration over layers ( #19497 )
...
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
2025-08-29 09:26:34 +08:00
Jee Jee Li
1b769dccf3
[Bugfix] Fix Ernie4_5_MoeForCausalLM shared experts ( #21717 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-07-28 11:02:25 +00:00
xyxinyang
c72f049cb4
[Model] Fix Ernie4.5MoE e_score_correction_bias parameter ( #21586 )
...
Signed-off-by: zhouchong <zhouchong03@baidu.com>
Co-authored-by: zhouchong <zhouchong03@baidu.com>
2025-07-25 06:02:53 -07:00
Jee Jee Li
466e878f2a
[Quantization] Enable BNB support for more MoE models ( #21100 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-07-18 17:52:02 -07:00
CSWYF3634076
e303dcf523
[Model] Add Ernie4.5 and Ernie4.5MoE Model Support ( #20220 )
...
Signed-off-by: wangyafeng <wangyafeng@baidu.com>
2025-07-02 03:37:01 -07:00
