 Allen WangandGitHub
|
c6cf9295e1
|
[Bugfix] Sets is_first_step_output for TPUModelRunner (#9202)
|
2024-10-11 13:28:10 -07:00 |
|
|
Wallas HenriqueandGitHub
|
8baf85e4e9
|
[Doc] Compatibility matrix for mutual exclusive features (#8512)
Signed-off-by: Wallas Santos <wallashss@ibm.com>
|
2024-10-11 11:18:50 -07:00 |
|
|
homeffjyandGitHub
|
1a1823871d
|
[Doc] Remove outdated comment to avoid misunderstanding (#9287)
|
2024-10-11 18:02:03 +00:00 |
|
|
sixgodandGitHub
|
6cf1167c1a
|
[Model] Add GLM-4v support and meet vllm==0.6.2 (#9242)
|
2024-10-11 17:36:13 +00:00 |
|
|
Burkhard RingleinandGitHub
|
f710090d8e
|
[Kernel] adding fused moe kernel config for L40S TP4 (#9245)
|
2024-10-11 08:54:22 -07:00 |
|
|
Tyler Michael SmithandGitHub
|
7342a7d7f8
|
[Model] Support Mamba (#6484)
|
2024-10-11 15:40:06 +00:00 |
|
|
Sebastian SchoennenbeckandGitHub
|
df3dcdf49d
|
[Bugfix] Fix priority in multiprocessing engine (#9277)
|
2024-10-11 15:35:35 +00:00 |
|
|
Jee Jee LiandGitHub
|
36ea79079b
|
[Misc][LoRA] Support loading LoRA weights for target_modules in reg format (#9275)
|
2024-10-11 12:31:21 +00:00 |
|
|
Cyrus LeungandGitHub
|
e808156f30
|
[Misc] Collect model support info in a single process per model (#9233)
|
2024-10-11 11:08:11 +00:00 |
|
|
|
cbc2ef5529
|
[misc] hide best_of from engine (#9261)
Co-authored-by: Brendan Wong <bjwpokemon@gmail.com>
|
2024-10-10 21:30:44 -07:00 |
|
|
youkaichaoandGitHub
|
e00c094f15
|
[torch.compile] generic decorators (#9258)
|
2024-10-10 15:54:23 -07:00 |
|
|
youkaichaoandGitHub
|
e4d652ea3e
|
[torch.compile] integration with compilation control (#9058)
|
2024-10-10 12:39:36 -07:00 |
|
|
whyiugandGitHub
|
04de9057ab
|
[Model] support input image embedding for minicpmv (#9237)
|
2024-10-10 15:00:47 +00:00 |
|
|
Isotr0pyandGitHub
|
07c11cf4d4
|
[Bugfix] Fix lm_head weights tying with lora for llama (#9227)
|
2024-10-10 21:11:56 +08:00 |
|
|
sroy745andGitHub
|
f3a507f1d3
|
[Core] Add an environment variable which needs to be set explicitly to allow BlockSpaceManagerV1 (#9149)
|
2024-10-10 14:17:17 +08:00 |
|
|
youkaichaoandGitHub
|
de895f1697
|
[misc] improve model support check in another process (#9208)
|
2024-10-09 21:58:27 -07:00 |
|
|
Russell BryantandGitHub
|
cf25b93bdd
|
[Core] Fix invalid args to _process_request (#9201)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
|
2024-10-10 12:10:09 +08:00 |
|
|
Russell BryantandGitHub
|
cdca8994bd
|
[CI/Build] mypy: check vllm/entrypoints (#9194)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
|
2024-10-09 17:15:28 +00:00 |
|
|
Li, JiangandGitHub
|
ca77dd7a44
|
[Hardware][CPU] Support AWQ for CPU backend (#7515)
|
2024-10-09 10:28:08 -06:00 |
|
|
Cyrus LeungandGitHub
|
cfaa6008e6
|
[Bugfix] Access get_vocab instead of vocab in tool parsers (#9188)
|
2024-10-09 08:59:57 -06:00 |
|
|
Ahmad Fahadh IlyasandGitHub
|
21906a6f50
|
[Bugfix] Fix lora loading for Compressed Tensors in #9120 (#9179)
|
2024-10-09 12:10:44 +00:00 |
|
|
youkaichaoandGitHub
|
c8627cd41b
|
[ci][test] use load dummy for testing (#9165)
|
2024-10-09 00:38:40 -07:00 |
|
|
Cyrus LeungandGitHub
|
8bfaa4e31e
|
[Bugfix] fix composite weight loading and EAGLE weight loading (#9160)
|
2024-10-09 00:36:55 -07:00 |
|
|
AlpinDaleandGitHub
|
0b5b5d767e
|
[Frontend] Log the maximum supported concurrency (#8831)
|
2024-10-09 00:03:14 -07:00 |
|
|
Hui LiuandGitHub
|
cdc72e3c80
|
[Model] Remap FP8 kv_scale in CommandR and DBRX (#9174)
|
2024-10-09 06:43:06 +00:00 |
|
|
Travis JohnsonandGitHub
|
480b7f40cf
|
[Misc] Improve validation errors around best_of and n (#9167)
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
|
2024-10-09 04:54:48 +00:00 |
|
|
chenqianfzhandGitHub
|
2f4117c38e
|
support bitsandbytes quantization with more models (#9148)
|
2024-10-08 19:52:19 -06:00 |
|
|
Russell BryantandGitHub
|
2a131965a8
|
mypy: check additional directories (#9162)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
|
2024-10-08 22:08:22 +00:00 |
|
|
bnellnmandGitHub
|
bd37b9fbe2
|
[Bugfix] Try to handle older versions of pytorch (#9086)
|
2024-10-08 14:28:12 -07:00 |
|
|
DanieleandGitHub
|
9a94ca4a5d
|
[Bugfix] fix OpenAI API server startup with --disable-frontend-multiprocessing (#8537)
|
2024-10-08 09:38:40 -07:00 |
|
|
Alex BrooksandGitHub
|
069d3bd8d0
|
[Frontend] Add Early Validation For Chat Template / Tool Call Parser (#9151)
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
|
2024-10-08 14:31:26 +00:00 |
|
|
Alex BrooksandGitHub
|
a3691b6b5e
|
[Core][Frontend] Add Support for Inference Time mm_processor_kwargs (#9131)
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
|
2024-10-08 14:12:56 +00:00 |
|
|
Brendan WongandGitHub
|
8c746226c9
|
[Frontend] API support for beam search for MQLLMEngine (#9117)
|
2024-10-08 05:51:43 +00:00 |
|
|
Kunshang JiandGitHub
|
80b57f00d5
|
[Intel GPU] Fix xpu decode input (#9145)
|
2024-10-08 03:51:14 +00:00 |
|
|
youkaichaoandGitHub
|
fa45513a51
|
[misc] fix comment and variable name (#9139)
|
2024-10-07 16:07:05 -07:00 |
|
|
|
151ef4efd2
|
[Model] Support NVLM-D and fix QK Norm in InternViT (#9045)
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2024-10-07 11:55:12 +00:00 |
|
|
Isotr0pyandGitHub
|
f19da64871
|
[Core] Refactor GGUF parameters packing and forwarding (#8859)
|
2024-10-07 10:01:46 +00:00 |
|
|
Isotr0pyandGitHub
|
4f95ffee6f
|
[Hardware][CPU] Cross-attention and Encoder-Decoder models support on CPU backend (#9089)
|
2024-10-07 06:50:35 +00:00 |
|
|
Cyrus LeungandGitHub
|
8c6de96ea1
|
[Model] Explicit interface for vLLM models and support OOT embedding models (#9108)
|
2024-10-07 06:10:35 +00:00 |
|
|
youkaichaoandGitHub
|
18b296fdb2
|
[core] remove beam search from the core (#9105)
|
2024-10-07 05:47:04 +00:00 |
|
|
sroy745andGitHub
|
c8f26bb636
|
[BugFix][Core] Fix BlockManagerV2 when Encoder Input is None (#9103)
|
2024-10-07 03:52:42 +00:00 |
|
|
Isotr0pyandGitHub
|
487678d046
|
[Bugfix][Hardware][CPU] Fix CPU model input for decode (#9044)
|
2024-10-06 19:14:27 -07:00 |
|
|
|
cb3b2b9ba4
|
[Bugfix] Fix incorrect updates to num_computed_tokens in multi-step scheduling (#9038)
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
|
2024-10-06 12:48:11 -07:00 |
|
|
Yanyi LiuandGitHub
|
fdf59d30ea
|
[Bugfix] fix tool_parser error handling when serve a model not support it (#8709)
|
2024-10-06 12:51:08 +00:00 |
|
|
|
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 |
|
|
Cyrus LeungandGitHub
|
f22619fe96
|
[Misc] Remove user-facing error for removed VLM args (#9104)
|
2024-10-06 01:33:52 -07:00 |
|
|
|
168cab6bbf
|
[Frontend] API support for beam search (#9087)
Co-authored-by: youkaichao <youkaichao@126.com>
|
2024-10-05 23:39:03 -07:00 |
|
|
TJianandGitHub
|
23fea8714a
|
[Bugfix] Fix try-catch conditions to import correct Flash Attention Backend in Draft Model (#9101)
|
2024-10-06 13:00:04 +08:00 |
|
|
youkaichaoandGitHub
|
f4dd830e09
|
[core] use forward context for flash infer (#9097)
|
2024-10-05 19:37:31 -07:00 |
|
|
Andy DaiandGitHub
|
5df1834895
|
[Bugfix] Fix order of arguments matters in config.yaml (#8960)
|
2024-10-05 17:35:11 +00:00 |
|