Cyrus Leung
cf73f0c95e
[Model] Enable optional prefix when loading embedding models ( #10639 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-25 18:14:33 +00:00
youkaichao
eebad39f26
[torch.compile] support all attention backends ( #10558 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-22 14:04:42 -08:00
Isotr0py
c4e464333e
[Misc] Add uninitialized params tracking for AutoWeightsLoader ( #10327 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2024-11-18 09:07:46 +08:00
Murali Andoorveedu
b2e0ad3b59
[Perf] Reduce peak memory usage of llama ( #10339 )
...
Signed-off-by: andoorve <37849411+andoorve@users.noreply.github.com>
2024-11-15 00:38:20 +00:00
Woosuk Kwon
bbd3e86926
[V1] Support VLMs with fine-grained scheduling ( #9871 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-11-13 04:53:13 +00:00
youkaichao
f89d18ff74
[6/N] pass whole config to inner model ( #10205 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-11 06:41:46 +00:00
youkaichao
1a95f10ee7
[5/N] pass the whole config to model ( #9983 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-09 14:17:28 +08:00
Joe Runde
d58268c56a
[V1] Make v1 more testable ( #9888 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2024-11-06 11:57:35 -08:00
Jee Jee Li
2003cc3513
[Model][LoRA]LoRA support added for LlamaEmbeddingModel ( #10071 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-11-06 09:49:19 +00:00
Aaron Pham
21063c11c7
[CI/Build] drop support for Python 3.8 EOL ( #8464 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-11-06 07:11:55 +00:00
Jee Jee Li
fb2716d641
[Misc]Reduce BNB static variable ( #9987 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-11-04 17:04:40 +00:00
Went-Liang
81f09cfd80
[Model] Support math-shepherd-mistral-7b-prm model ( #9697 )
...
Signed-off-by: Went-Liang <wenteng_liang@163.com>
2024-10-30 09:33:42 -07:00
Michael Goin
bc73e9821c
[Bugfix] Fix prefix strings for quantized VLMs ( #9772 )
2024-10-29 16:02:59 -07:00
wangshuai09
4e2d95e372
[Hardware][ROCM] using current_platform.is_rocm ( #9642 )
...
Signed-off-by: wangshuai09 <391746016@qq.com>
2024-10-28 04:07:00 +00:00
youkaichao
17c79f3c36
[torch.compile] auto infer dynamic_arg_dims from type annotation ( #9589 )
2024-10-22 13:43:37 -07:00
Cyrus Leung
7abba39ee6
[Model] VLM2Vec, the first multimodal embedding model in vLLM ( #9303 )
2024-10-16 14:31:00 +08:00
youkaichao
e00c094f15
[torch.compile] generic decorators ( #9258 )
2024-10-10 15:54:23 -07:00
youkaichao
e4d652ea3e
[torch.compile] integration with compilation control ( #9058 )
2024-10-10 12:39:36 -07:00
Isotr0py
07c11cf4d4
[Bugfix] Fix lm_head weights tying with lora for llama ( #9227 )
2024-10-10 21:11:56 +08:00
Cyrus Leung
8bfaa4e31e
[Bugfix] fix composite weight loading and EAGLE weight loading ( #9160 )
2024-10-09 00:36:55 -07:00
chenqianfzh
2f4117c38e
support bitsandbytes quantization with more models ( #9148 )
2024-10-08 19:52:19 -06:00
Isotr0py
f19da64871
[Core] Refactor GGUF parameters packing and forwarding ( #8859 )
2024-10-07 10:01:46 +00:00
Cyrus Leung
b22b798471
[Model] PP support for embedding models and update docs ( #9090 )
...
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
2024-10-06 16:35:27 +08:00
Murali Andoorveedu
0f6d7a9a34
[Models] Add remaining model PP support ( #7168 )
...
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
Signed-off-by: Murali Andoorveedu <muralidhar.andoorveedu@centml.ai>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-10-04 10:56:58 +08:00
Patrick von Platen
29f49cd6e3
[Model] Allow loading from original Mistral format ( #8168 )
...
Co-authored-by: Michael Goin <michael@neuralmagic.com>
2024-09-06 17:02:05 -06:00
afeldman-nm
428dd1445e
[Core] Logprobs support in Multi-step ( #7652 )
2024-08-29 19:19:08 -07:00
Cyrus Leung
7025b11d94
[Bugfix] Fix weight loading for Chameleon when TP>1 ( #7410 )
2024-08-13 05:33:41 +00:00
Isotr0py
360bd67cf0
[Core] Support loading GGUF model ( #5191 )
...
Co-authored-by: Michael Goin <michael@neuralmagic.com>
2024-08-05 17:54:23 -06:00
Travis Johnson
630dd9e0ae
[Bugfix][Model] Skip loading lm_head weights if using tie_word_embeddings ( #6758 )
...
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
2024-07-31 19:49:11 -07:00
Alphi
2f4e108f75
[Bugfix] Clean up MiniCPM-V ( #6939 )
...
Co-authored-by: hezhihui <hzh7269@modelbest.cn>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2024-07-31 14:39:19 +00:00
Alphi
9e169a4c61
[Model] Adding support for MiniCPM-V ( #4087 )
2024-07-24 20:59:30 -07:00
Michael Goin
9e0b558a09
[Misc] Support FP8 kv cache scales from compressed-tensors ( #6528 )
2024-07-23 04:11:50 +00:00
Robert Shaw
dbe5588554
[ Misc ] non-uniform quantization via compressed-tensors for Llama ( #6515 )
2024-07-18 22:39:18 -04:00
Michael Goin
15c6a079b1
[Model] Support Mistral-Nemo ( #6548 )
2024-07-18 20:31:50 +00:00
Wushi Dong
1d094fd7c0
[Distributed][PP] only create embedding & lm head when necessary ( #6455 )
...
original title: [Distributed][Model] Rank-based Component Creation for Pipeline Parallelism Memory Optimization
2024-07-16 19:20:26 -07:00
Michael Goin
978aed5300
[Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale ( #6081 )
2024-07-16 15:31:32 -07:00
youkaichao
69672f116c
[core][distributed] simplify code to support pipeline parallel ( #6406 )
2024-07-14 21:20:51 -07:00
Qubitium-ModelCloud
ee93f4f92a
[CORE] Quantized lm-head Framework ( #4442 )
...
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
Co-authored-by: ZX <zx@lbx.dev>
2024-07-02 22:25:17 +00:00
Murali Andoorveedu
c5832d2ae9
[Core] Pipeline Parallel Support ( #4412 )
...
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
2024-07-02 10:58:08 -07:00
Cyrus Leung
98cf2ed678
[Model][Bugfix] Implicit model flags and reenable Phi-3-Vision ( #5896 )
2024-06-27 09:08:10 -07:00
Cyrus Leung
96354d6a29
[Model] Add base class for LoRA-supported models ( #5018 )
2024-06-27 16:03:04 +08:00
chenqianfzh
b9c0605a8e
[Feature][Kernel] Support bitsandbytes quantization and QLoRA ( #4776 )
2024-06-01 14:51:10 -06:00
Zhuohan Li
1102bef219
[Bugfix / Core] Prefix Caching Guards (merged with main) ( #4846 )
...
Co-authored-by: rsnm2 <rshaw@neuralmagic.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>
2024-05-27 15:18:17 -07:00
Dipika Sikka
a1242324c9
[Kernel] Initial Activation Quantization Support ( #4525 )
...
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2024-05-23 21:29:18 +00:00
Philipp Moritz
a36de682d4
[Minor] Fix small typo in llama.py: QKVParallelLinear -> QuantizationConfig ( #4991 )
2024-05-22 22:26:56 +00:00
Cody Yu
a3a73ab069
[Misc] Load FP8 kv-cache scaling factors from checkpoints ( #4893 )
...
The 2nd PR for #4532 .
This PR supports loading FP8 kv-cache scaling factors from a FP8 checkpoint (with .kv_scale parameter).
2024-05-22 13:28:20 -07:00
SangBin Cho
2e9a2227ec
[Lora] Support long context lora ( #4787 )
...
Currently we need to call rotary embedding kernel for each LoRA, which makes it hard to serve multiple long context length LoRA. Add batched rotary embedding kernel and pipe it through.
It replaces the rotary embedding layer to the one that is aware of multiple cos-sin-cache per scaling factors.
Follow up of https://github.com/vllm-project/vllm/pull/3095/files
2024-05-18 16:05:23 +09:00
Woosuk Kwon
0fca3cdcf2
[Misc] Enhance attention selector ( #4751 )
2024-05-13 10:47:25 -07:00
Yikang Shen
6eaccb7353
[Model] Add support for IBM Granite Code models ( #4636 )
2024-05-11 21:27:24 -07:00
Cody Yu
a62aaf1df5
[Misc][Refactor] Generalize linear_method to be quant_method ( #4373 )
2024-04-26 16:41:14 -04:00
