 Roger Wang
|
0f3f3c86ec
|
[Bugfix] Update attention interface in Whisper (#11784)
Signed-off-by: Roger Wang <ywang@roblox.com>
|
2025-01-07 04:36:24 +00:00 |
|
|
Cyrus Leung
|
d0169e1b0f
|
[Model] Future-proof Qwen2-Audio multi-modal processor (#11776)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-01-07 11:05:17 +08:00 |
|
|
Cyrus Leung
|
08fb75c72e
|
[Bugfix] Fix LLaVA-NeXT feature size precision error (for real) (#11772)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-01-07 01:10:54 +00:00 |
|
|
Roger WangandDarkLight1337
|
91b361ae89
|
[V1] Extend beyond image modality and support mixed-modality inference with Llava-OneVision (#11685)
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-01-06 19:58:16 +00:00 |
|
|
Chen Zhang
|
e20c92bb61
|
[Kernel] Move attn_type to Attention.__init__() (#11690)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
|
2025-01-07 00:11:28 +08:00 |
|
|
Jee Jee Li
|
32c9eff2ff
|
[Bugfix][V1] Fix molmo text-only inputs (#11676)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-01-06 15:22:25 +00:00 |
|
|
Roger Wang
|
9279b9f83d
|
[Bugfix] Fix max image size for LLaVA-Onevision (#11769)
Signed-off-by: Roger Wang <ywang@roblox.com>
|
2025-01-06 13:48:53 +00:00 |
|
|
Cyrus Leung
|
996357e480
|
[VLM] Separate out profiling-related logic (#11746)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-01-06 16:02:21 +08:00 |
|
|
Lucas Tuckerandlucast2021
|
9c749713f6
|
[mypy] Forward pass function type hints in lora (#11740)
Signed-off-by: lucast2021 <lucast2021@headroyce.org>
Co-authored-by: lucast2021 <lucast2021@headroyce.org>
|
2025-01-06 07:59:36 +00:00 |
|
|
Cyrus LeungandIsotr0py
|
65c08928c2
|
[Model] Remove unnecessary weight initialization logic (#11736)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
|
2025-01-04 23:46:21 +08:00 |
|
|
Cyrus Leung
|
ba214dffbe
|
[Bugfix] Fix precision error in LLaVA-NeXT (#11735)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-01-04 23:45:57 +08:00 |
|
|
Cyrus Leung
|
eed11ebee9
|
[VLM] Merged multi-modal processors for LLaVA-NeXT-Video and LLaVA-OneVision (#11717)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-01-04 11:40:53 +00:00 |
|
|
Jee Jee LiandIsotr0py
|
a655eb3025
|
[Misc]Add BNB quantization for Qwen2VL (#11719)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
|
2025-01-03 15:19:02 -07:00 |
|
|
Aurick QiaoandAurick Qiao
|
e1a5c2f0a1
|
[Model] Whisper model implementation (#11280)
Co-authored-by: Aurick Qiao <aurick.qiao@snowflake.com>
|
2025-01-03 16:39:19 +08:00 |
|
|
Lu Fang
|
07064cb1d4
|
[Bugfix] Check chain_speculative_sampling before calling it (#11673)
Signed-off-by: Lu Fang <lufang@fb.com>
|
2025-01-02 16:58:56 -08:00 |
|
|
bjmsongandbjmsong
|
187e32997c
|
[Bugfix] Change kv scaling factor by param json on nvidia gpu (#11688)
Signed-off-by: bjmsong <bjmsong@126.com>
Co-authored-by: bjmsong <bjmsong@126.com>
|
2025-01-02 21:11:39 +00:00 |
|
|
Cyrus Leung
|
8c38ee7007
|
[VLM] Merged multi-modal processor for LLaVA-NeXT (#11682)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-01-02 16:39:27 +00:00 |
|
|
Cyrus LeungandIsotr0py
|
a115ac46b5
|
[VLM] Move supported limits and max tokens to merged multi-modal processor (#11669)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
|
2025-01-01 15:44:42 +00:00 |
|
|
Kazuhiro Serizawa
|
6d70198b17
|
[Doc] Fix typo (#11666)
Signed-off-by: Kazuhiro Serizawa <nserihiro@gmail.com>
|
2025-01-01 08:10:10 +00:00 |
|
|
Jee Jee Li
|
11d8a091c6
|
[Misc] Optimize Qwen2-VL LoRA test (#11663)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-01-01 14:42:23 +08:00 |
|
|
Cyrus LeungandRoger Wang
|
365801fedd
|
[VLM] Add max-count checking in data parser for single image models (#11661)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
|
2024-12-31 22:15:21 -08:00 |
|
|
|
e7c7c5e822
|
[V1][VLM] V1 support for selected single-image models. (#11632)
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Isotr0py <2037008807@qq.com>
|
2024-12-31 21:17:22 +00:00 |
|
|
Michael Goin
|
74fa1d123c
|
[Bugfix] Fix OpenAI parallel sampling when using xgrammar (#11637)
Signed-off-by: mgoin <michael@neuralmagic.com>
|
2024-12-31 03:43:54 +00:00 |
|
|
|
a2a40bcd0d
|
[Model][LoRA]LoRA support added for MolmoForCausalLM (#11439)
Signed-off-by: Matthias Vogler <matthias.vogler@joesecurity.org>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Matthias Vogler <matthias.vogler@joesecurity.org>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2024-12-30 17:33:06 -08:00 |
|
|
whyiug
|
36e7670045
|
[Bugfix] Validate and concatenate image embeddings in MiniCPMVBaseModel (#11631)
|
2024-12-30 18:51:04 +00:00 |
|
|
Cyrus Leung
|
8d9b6721e7
|
[VLM] Abstract out multi-modal data parsing in merged processor (#11620)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2024-12-30 15:01:35 +00:00 |
|
|
youkaichao
|
b12e87f942
|
[platforms] enable platform plugins (#11602)
Signed-off-by: youkaichao <youkaichao@gmail.com>
|
2024-12-30 20:24:45 +08:00 |
|
|
Li, Jiang
|
5dbf854553
|
[CI/Build][CPU] Fix CPU CI by lazy importing triton FP8 kernels (#11618)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2024-12-30 10:17:04 +00:00 |
|
|
Michael Goin
|
0aa38d16f5
|
Remove print statement in DeepseekScalingRotaryEmbedding (#11604)
|
2024-12-29 20:16:46 +00:00 |
|
|
youkaichao
|
dba4d9dec6
|
[v1][bugfix] fix cudagraph with inplace buffer assignment (#11596)
Signed-off-by: youkaichao <youkaichao@gmail.com>
|
2024-12-29 09:03:49 +00:00 |
|
|
youkaichao
|
328841d002
|
[bugfix] interleaving sliding window for cohere2 model (#11583)
Signed-off-by: youkaichao <youkaichao@gmail.com>
|
2024-12-28 16:55:42 +00:00 |
|
|
Roger Wang
|
b7dcc003dc
|
[Model] Remove hardcoded image tokens ids from Pixtral (#11582)
Signed-off-by: Roger Wang <ywang@roblox.com>
|
2024-12-28 10:54:23 +00:00 |
|
|
Isotr0pyandCyrus Leung
|
d34be24bb1
|
[Model] Support InternLM2 Reward models (#11571)
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
|
2024-12-28 06:14:10 +00:00 |
|
|
Selali
|
ac79799403
|
[Bugfix] Fix for ROCM compressed tensor support (#11561)
|
2024-12-27 20:12:11 +00:00 |
|
|
Isotr0py
|
dde1fa18c9
|
[Misc] Improve BNB loader to handle mixture of sharded and merged weights with same suffix (#11566)
Signed-off-by: Isotr0py <2037008807@qq.com>
|
2024-12-27 19:45:13 +00:00 |
|
|
Jee Jee Li
|
0240402c46
|
[Misc]Add BNB quantization for MolmoForCausalLM (#11551)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2024-12-27 18:48:24 +00:00 |
|
|
ErezSC42
|
55509c2114
|
[MODEL] LoRA support for Jamba model (#11209)
Signed-off-by: Erez Schwartz <erezs@ai21.com>
|
2024-12-27 17:58:21 +00:00 |
|
|
Cyrus Leung
|
101418096f
|
[VLM] Support caching in merged multi-modal processor (#11396)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2024-12-27 17:22:48 +00:00 |
|
|
Jee Jee Li
|
2c9b8ea2b0
|
[Bugfix] Fix TeleChat2ForCausalLM weights mapper (#11546)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2024-12-27 10:39:15 +00:00 |
|
|
Mengqing Cao
|
6c6f7fe8a8
|
[Platform] Move model arch check to platform (#11503)
Signed-off-by: Mengqing Cao <cmq0113@163.com>
|
2024-12-27 08:45:25 +00:00 |
|
|
Robert Shaw
|
2339d59f92
|
[BugFix] Fix quantization for all other methods (#11547)
|
2024-12-26 22:23:29 -08:00 |
|
|
|
f49777ba62
|
Deepseek v3 (#11502)
Signed-off-by: mgoin <michael@neuralmagic.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
Co-authored-by: robertgshaw2-neuralmagic <rshaw@neuralmagic.com>
|
2024-12-26 16:09:44 -08:00 |
|
|
|
2072924d14
|
[Model] [Quantization] Support deepseek_v3 w8a8 fp8 block-wise quantization (#11523)
Signed-off-by: mgoin <michael@neuralmagic.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
Signed-off-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: simon-mo <simon.mo@hey.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: HandH1998 <1335248067@qq.com>
|
2024-12-26 15:33:30 -08:00 |
|
|
Cyrus Leung
|
eec906d811
|
[Misc] Add placeholder module (#11501)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2024-12-26 13:12:51 +00:00 |
|
|
Jee Jee Li
|
f57ee5650d
|
[Model] Modify MolmoForCausalLM MLP (#11510)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2024-12-26 13:12:05 +00:00 |
|
|
sroy745andWoosuk Kwon
|
dcb1a944d4
|
[V1] Adding min tokens/repetition/presence/frequence penalties to V1 sampler (#10681)
Signed-off-by: Sourashis Roy <sroy@roblox.com>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2024-12-26 19:02:58 +09:00 |
|
|
Cyrus Leung
|
3f3e92e1f2
|
[Model] Automatic conversion of classification and reward models (#11469)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2024-12-24 18:22:22 +00:00 |
|
|
Jee Jee Li
|
196c34b0ac
|
[Misc] Move weights mapper (#11443)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2024-12-24 13:05:25 +00:00 |
|
|
Jee Jee Li
|
b1b1038fbd
|
[Bugfix] Fix Qwen2-VL LoRA weight loading (#11430)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2024-12-24 09:56:10 +00:00 |
|
|
Michael Goin
|
60fb4f3bcf
|
[Bugfix] Add kv cache scales to gemma2.py (#11269)
|
2024-12-23 19:30:45 +00:00 |
|