 Tristan Leclercq
|
6220f3c6b0
|
[Bugfix] Fix transformers model impl ignored for mixtral quant (#18602)
Signed-off-by: Tristan Leclercq <tristanleclercq@gmail.com>
|
2025-05-23 05:54:13 -07:00 |
|
|
Harry Mellor
|
2edb533af2
|
Replace {func} with mkdocs style links (#18610)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-05-23 05:51:38 -07:00 |
|
|
Kay Yan
|
7ab056c273
|
[Hardware][CPU] Update intel_extension_for_pytorch 2.7.0 and move to requirements/cpu.txt (#18542)
Signed-off-by: Kay Yan <kay.yan@daocloud.io>
|
2025-05-23 04:38:42 -07:00 |
|
|
Madeesh KannanandRussell Bryant
|
e493e48524
|
[V0][Bugfix] Fix parallel sampling performance regression when guided decoding is enabled (#17731)
Signed-off-by: Madeesh Kannan <shadeMe@users.noreply.github.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
|
2025-05-23 03:38:23 -07:00 |
|
|
Mengqing Cao
|
4ce64e2df4
|
[Bugfix][Model] Fix baichuan model loader for tp (#18597)
Signed-off-by: Mengqing Cao <cmq0113@163.com>
|
2025-05-23 02:39:05 -07:00 |
|
|
Harry Mellor
|
a1fe24d961
|
Migrate docs from Sphinx to MkDocs (#18145)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-05-23 02:09:53 -07:00 |
|
|
Benjamin ChislettandWoosuk Kwon
|
583507d130
|
[Spec Decode] Make EAGLE3 draft token ID mapping optional (#18488)
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-05-22 20:17:39 -07:00 |
|
|
Harry Mellor
|
4b0da7b60e
|
Enable hybrid attention models for Transformers backend (#18494)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-05-23 10:12:08 +08:00 |
|
|
Mark McLoughlin
|
c6b636f9fb
|
[V1][Spec Decoding] Use model_loader.get_model() to load models (#18273)
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
|
2025-05-23 02:05:44 +00:00 |
|
|
Chenheli Hua
|
04eb88dc80
|
Re-submit: Fix: Proper RGBA -> RGB conversion for PIL images. (#18569)
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
|
2025-05-23 01:59:18 +00:00 |
|
|
Sanger Steel
|
c32e249a23
|
[Frontend] [Core] Add Tensorizer support for V1, LoRA adapter serialization and deserialization (#17926)
Signed-off-by: Sanger Steel <sangersteel@gmail.com>
|
2025-05-22 18:44:18 -07:00 |
|
|
Tyler Michael SmithandLucas Wilkinson
|
6e588da0f4
|
[Build/CI] Fix CUDA 11.8 build (#17679)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
|
2025-05-22 12:13:54 -07:00 |
|
|
|
fa72f9a812
|
Order sequence ids + config update to support specifying custom quantization layers (#18279)
Signed-off-by: Elaine Zhao <elaineyz@amazon.com>
Co-authored-by: Tailin Pan <tailinpa@amazon.com>
Co-authored-by: Rishabh Rajesh <rishyraj@amazon.com>
Co-authored-by: Yishan McNabb <yishanm@amazon.com>
Co-authored-by: Patrick Lange <patlange@amazon.com>
Co-authored-by: Maxwell Goldberg <mgld@amazon.com>
Co-authored-by: Aakash Shetty <sheaak@amazon.com>
|
2025-05-22 02:20:36 -07:00 |
|
|
|
ebed81fbf5
|
Update default neuron config for speculation (#18274)
Signed-off-by: Elaine Zhao <elaineyz@amazon.com>
Co-authored-by: Shashwat Srijan <sssrijan@amazon.com>
Co-authored-by: Aakash Shetty <sheaak@amazon.com>
|
2025-05-22 02:18:55 -07:00 |
|
|
Shane A
|
51797775c3
|
[Bugfix][Model] Make Olmo2Model weight loading return loaded weights (#18504)
Signed-off-by: Shane A <shanea@allenai.org>
|
2025-05-21 21:17:03 -07:00 |
|
|
youngrok cha
|
d022115cc6
|
[Bugfix] Inconsistent token calculation compared to HF in llava family (#18479)
Signed-off-by: jaycha <jaycha@ncsoft.com>
|
2025-05-21 20:21:47 -07:00 |
|
|
|
20bd6f4d2e
|
[FalconH1] Fix output dtype in RMSNorm fallback path for Falcon-H1 (e.g. 0.5B) (#18500)
Signed-off-by: dhia.rhaiem <dhia.rhaiem@tii.ae>
Co-authored-by: younesbelkada <younesbelkada@gmail.com>
Co-authored-by: Ilyas Chahed <ilyas.chahed@tii.ae>
Co-authored-by: Jingwei Zuo <jingwei.zuo@tii.ae>
|
2025-05-21 19:23:59 -07:00 |
|
|
GiantCroc
|
c154d89306
|
[Doc] fix arg docstring in linear layers (#18410)
Signed-off-by: giantcroc <1204449533@qq.com>
|
2025-05-21 06:45:57 -07:00 |
|
|
|
eca18691d2
|
[MODEL] FalconH1 (#18406)
Signed-off-by: dhia.rhaiem <dhia.rhaiem@tii.ae>
Co-authored-by: younesbelkada <younesbelkada@gmail.com>
Co-authored-by: Ilyas Chahed <ilyas.chahed@tii.ae>
Co-authored-by: Jingwei Zuo <jingwei.zuo@tii.ae>
|
2025-05-21 04:59:06 -07:00 |
|
|
Gregory Shtrasberg
|
0c15c2e486
|
[Bugfix] config.head_dim is now explicitly set to None (#18432)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
|
2025-05-20 21:04:33 -07:00 |
|
|
Michael Goin
|
3b17ea26e4
|
[TPU] Re-enable the Pallas MoE kernel (#18025)
Signed-off-by: Michael Goin <mgoin64@gmail.com>
|
2025-05-20 19:52:27 -07:00 |
|
|
Calvin Chen
|
e1f5a71ed7
|
[Model] use AutoWeightsLoader for bloom (#18300)
Signed-off-by: calvin chen <120380290@qq.com>
|
2025-05-20 09:40:05 -07:00 |
|
|
Michael Goin
|
f4a8a37465
|
[Minor] Rename quantization nvfp4 to modelopt_fp4 (#18356)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-05-20 09:08:37 -07:00 |
|
|
Random Fly
|
bca55b556f
|
[Bugfix] fix adding bias twice in ipex GPTQ quantization (#18363)
Signed-off-by: rand-fly <randfly@outlook.com>
|
2025-05-20 00:54:33 -07:00 |
|
|
Isotr0py
|
f07a673eb2
|
[Misc] Allow AutoWeightsLoader to skip loading weights with specific substr in name (#18358)
Signed-off-by: Isotr0py <2037008807@qq.com>
|
2025-05-19 20:20:12 -07:00 |
|
|
Satyajith Chilappagari
|
dc1440cf9f
|
Neuron up mistral (#18222)
Signed-off-by: Satyajith Chilappagari <satchill@amazon.com>
|
2025-05-19 09:54:47 -07:00 |
|
|
sunyicode0012
|
7937c2fd52
|
Add files via uploadAdd fused MoE kernel tuning configs (fp8_w8a8) for DeepSeek V3/R1 on a single-node 8x NVIDIA H20 96GB setup (#18337)
|
2025-05-19 09:49:57 -07:00 |
|
|
Wenhua Cheng
|
e2ee1e8e9e
|
[Feature]Add support for models quantized with AutoRound (#17850)
Signed-off-by: wenhuach21 <wenhua.cheng@intel.com>
|
2025-05-19 09:38:53 -07:00 |
|
|
Jee Jee Li
|
6781af5608
|
[Quantization] Pool model support bitsandbytes (#18087)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-05-19 09:03:43 -07:00 |
|
|
Shaoyu Yangandcascade
|
d637b96099
|
[BugFix] [Vul] Add missing usedforsecurity=False in MD5 hashing to enable FIPS (#18319)
Signed-off-by: cascade812 <cascade812@outlook.com>
Signed-off-by: shaoyuyoung <shaoyuyoung@gmail.com>
Co-authored-by: cascade <cascade812@outlook.com>
|
2025-05-19 01:31:23 -07:00 |
|
|
CYJiang
|
275c5daeb0
|
fix: Add type specifications for CLI arguments in tensorizer options (#18314)
|
2025-05-18 23:42:17 -07:00 |
|
|
wwl2755
|
9da1095daf
|
[Spec Decode][V0] Fix spec decode correctness test in V0 eagle/medusa (#18175)
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
|
2025-05-18 19:49:46 -07:00 |
|
|
Lifu Huang
|
4fb349f66a
|
Fix copy-paste error in phi4mm image processing (#18315)
Signed-off-by: Lifu Huang <lifu.hlf@gmail.com>
|
2025-05-18 07:00:12 -07:00 |
|
|
22quinn
|
908733aca7
|
[Model] Use sigmoid for single-label classification (#18313)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
|
2025-05-18 07:00:09 -07:00 |
|
|
rongfu.leng
|
9214e60631
|
[Model] use AutoWeightsLoader for solar (#18113)
|
2025-05-17 00:24:17 -07:00 |
|
|
Bowen Wangandmgoin
|
7fdfa01530
|
[Sampler] Adapt to FlashInfer 0.2.3 sampler API (#15777)
Signed-off-by: Bowen Wang <abmfy@icloud.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2025-05-16 15:14:03 -07:00 |
|
|
learner0810
|
87d871470d
|
[Model] Use autoweightloader for dbrx (#18251)
Signed-off-by: learner0810 <zhongjun.li@daocloud.io>
|
2025-05-16 07:54:13 -07:00 |
|
|
Lain
|
e23564cb70
|
use ceil_div in cutlass block scaling shape check (#17918)
|
2025-05-16 03:02:58 -07:00 |
|
|
Vadim Gimpelson
|
67da5720d4
|
[PERF] Speed up Qwen2.5-VL model by speed up rotary position embedding (#17973)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@centml.ai>
|
2025-05-15 23:31:02 -07:00 |
|
|
Sky Leeandlisiqi23
|
f4937a51c1
|
[Model] vLLM v1 supports Medusa (#17956)
Signed-off-by: lisiqi23 <lisiqi23@xiaomi.com>
Signed-off-by: skylee-01 <497627264@qq.com>
Co-authored-by: lisiqi23 <lisiqi23@xiaomi.com>
|
2025-05-15 21:05:31 -07:00 |
|
|
TJian
|
92540529c0
|
[Bugfix] [ROCm]: Remove assertion logic when using AITER fused moe in unquantizedMethod to reenable LLama4 BF16 (#18205)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2025-05-15 09:53:18 -07:00 |
|
|
Harry Mellor
|
07ad27121f
|
Update deprecated type hinting in model_loader (#18130)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-05-15 04:00:21 -07:00 |
|
|
omahs
|
a9944aabfa
|
fix: typos (#18151)
Signed-off-by: omahs <73983677+omahs@users.noreply.github.com>
|
2025-05-15 02:16:15 -07:00 |
|
|
Mengqing Cao
|
70f8b96724
|
[Bugfix] Fix FusedMoEPrepareAndFinalize for cuda-disalike backends (#18178)
Signed-off-by: Mengqing Cao <cmq0113@163.com>
|
2025-05-14 23:16:31 -07:00 |
|
|
inkcherry
|
dd2a94596a
|
[Model] Allow the use of sliding window in Qwen2 (#17772)
Signed-off-by: inkcherry <mingzhi.liu@intel.com>
|
2025-05-14 22:29:38 -07:00 |
|
|
Harry Mellor
|
26d0419309
|
Update deprecated type hinting in models (#18132)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-05-14 22:06:50 -07:00 |
|
|
Jerry Zhang
|
7974736740
|
Add support for loading torchao models with AOPerModuleConfig (#17826)
Signed-off-by: Jerry Zhang <jerryzh168@gmail.com>
|
2025-05-14 16:24:59 -07:00 |
|
|
bnellnm
|
f9c069c85e
|
Modularize fused experts and integrate PPLX kernels (#15956)
|
2025-05-14 13:11:54 -07:00 |
|
|
|
418d2f8bfb
|
[V1][Spec Decode] Share input embedding of target model with EAGLE draft model to free ~1GB for llama 3 model (#17326)
Co-authored-by: root <root@ekagra-8xh100.us-east5-a.c.serving-efficiency-poc.internal>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-05-14 12:31:46 -07:00 |
|
|
Cyrus Leung
|
d62a076e84
|
[Model] GritLM supports other attention backends (#18109)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-05-14 03:33:19 -07:00 |
|