Henry Tsang
094b7d9496
[Kernel][Build/CI] Bump CUTLASS to 3.8 and add initializers for cutlass epilogues ( #13797 )
2025-02-25 18:52:03 -08:00
Chenguang Li
e1fe7591f2
[Misc]Code Cleanup ( #13859 )
...
Signed-off-by: noemotiovon <noemotiovon@gmail.com>
Co-authored-by: noemotiovon <noemotiovon@gmail.com>
2025-02-26 10:44:30 +08:00
Lily Liu
5629f26df7
[V1][Spec Decode] Change Spec Decode Rejection Sampling API ( #13729 )
2025-02-25 18:14:48 -08:00
Rui Qiao
9ba28043b5
[misc] Show driver IP info when Ray fails to allocate driver worker ( #13858 )
...
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
2025-02-26 09:53:43 +08:00
Harry Mellor
24679788ed
DeepSeek V2/V3/R1 only place lm_head on last pp rank ( #13833 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-02-26 01:24:57 +00:00
Michael Goin
07c4353057
[Model] Support Grok1 ( #13795 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-02-26 01:07:12 +00:00
Harry Mellor
34e3494e70
Fix failing MyGemma2Embedding test ( #13820 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-02-25 12:33:03 -08:00
Liangfu Chen
f75aa72732
[Neuron] Add custom_ops for neuron backend ( #13246 )
...
Signed-off-by: Liangfu Chen <liangfc@amazon.com>
Co-authored-by: George Novack <gnovack@amazon.com>
Co-authored-by: Aoyu Zhang <aoyuzhan@amazon.com>
2025-02-25 11:47:49 -08:00
Chen1022
340e39e387
Fix string parsing error ( #13825 )
2025-02-25 08:20:29 -08:00
Cyrus Leung
f4133ce4e5
[Bugfix] Revert inspection code in #13743 ( #13832 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-02-26 00:18:50 +08:00
Wen Sun
6522d55b6f
Fix /v1/audio/transcriptions Bad Request Error ( #13811 )
2025-02-25 06:03:33 -08:00
Isotr0py
6ff518626c
[Bugfix] Fix deepseek-vl2 inference with more than 2 images ( #13818 )
2025-02-25 06:03:02 -08:00
Nichols A. Romero
fa82074167
[Bugfix] Flush TunableOp results before worker processes are destroyed. ( #13623 )
...
Signed-off-by: Nichols A. Romero <nick.romero@amd.com>
2025-02-25 11:08:20 +00:00
Junlin Zhou
75e9d49796
[Bugfix] Initialize attention bias on the same device as Query/Key/Value ( #13468 )
2025-02-25 02:13:09 -08:00
Chen1022
32c3b6bfd1
[Misc]Clarify Error Handling for Non-existent Model Paths and HF Repo IDs ( #13724 )
...
Signed-off-by: Chen-0210 <chenjincong11@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
2025-02-25 10:12:19 +00:00
Jee Jee Li
37b6cb4985
[CI/Build] Fix V1 LoRA failure ( #13767 )
2025-02-25 02:01:15 -08:00
Gregory Shtrasberg
aabeb2688f
[ROCm][Quantization][Kernel] Using HIP FP8 header ( #12593 )
2025-02-25 00:39:59 -08:00
Jiayi Yao
2f42a4888c
[Feature] Support KV cache offloading and disagg prefill with LMCache connector. ( #12953 )
2025-02-25 00:38:42 -08:00
Rui Qiao
3173c3b34e
[misc] Clean up ray compiled graph type hints ( #13731 )
2025-02-25 00:37:08 -08:00
Shanshan Shen
2d87d7d1ac
[Bugfix] Modify modelscope api usage in transformer_utils ( #13807 )
2025-02-25 00:36:07 -08:00
Russell Bryant
aab392774b
[Core] xgrammar: Expand list of unsupported jsonschema keywords ( #13783 )
...
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-02-25 08:21:25 +00:00
Cyrus Leung
6724e79164
[Misc] Check that the model can be inspected upon registration ( #13743 )
2025-02-25 00:18:19 -08:00
Varun Sundar Rabindranath
03f48b3db6
[Core] LoRA V1 - Add add/pin/list/remove_lora functions ( #13705 )
2025-02-25 00:18:02 -08:00
Michael Goin
4d251ad00e
Fix CompressedTensorsWNA16MoE with grouped scales ( #13769 )
2025-02-25 00:17:14 -08:00
Michael Goin
18e505930d
[Bugfix] Support MLA for CompressedTensorsWNA16 ( #13725 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-02-25 06:10:31 +00:00
Lucas Wilkinson
4a8cfc7551
[Bugfix] Fix deepseek-v2 error: "missing 1 required positional argument: 'residual'" ( #13802 )
2025-02-24 20:33:59 -08:00
Mark McLoughlin
bc32bc73aa
[V1][Metrics] Implement vllm:lora_requests_info metric ( #13504 )
2025-02-24 20:01:33 -08:00
wangxiyuan
ab1091d5f2
[Misc][Attention][Quantization] init property earlier ( #13733 )
...
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-02-25 03:19:30 +00:00
Tyler Michael Smith
1e15aaef56
[Bugfix][Quantization] Fix FP8 + EP ( #13784 )
...
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
2025-02-25 10:54:17 +08:00
cjackal
51010a1807
[Misc] set single whitespace between log sentences ( #13771 )
...
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
2025-02-25 10:26:12 +08:00
Eli Boyarski
7196a3b1db
[Doc] arg_utils.py: fixed a typo ( #13785 )
2025-02-24 18:23:04 -08:00
Harry Mellor
cdc1fa12eb
Remove unused kwargs from model definitions ( #13555 )
2025-02-24 17:13:52 -08:00
Robert Shaw
f61528d46d
[Misc][Chore] Clean Up AsyncOutputProcessing Logs ( #13780 )
2025-02-24 16:39:07 -08:00
Robert Shaw
1f0ae3ed0a
[Misc] Clean Up EngineArgs.create_engine_config ( #13734 )
...
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
2025-02-24 13:52:21 -05:00
Michael Goin
db986c19ea
Fix precommit fail in fused_moe intermediate_cache2 chunking ( #13772 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-02-24 09:25:47 -08:00
Roger Wang
227578480d
Revert "[V1][Core] Fix memory issue with logits & sampling" ( #13775 )
2025-02-24 09:16:05 -08:00
afeldman-nm
befc402d34
[V1] V1 engine implements parallel sampling (AsyncLLM and LLMEngine) ( #10980 )
...
Signed-off-by: Andrew Feldman <afeldman@neuralmagic.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-02-24 08:29:41 -08:00
Nicolò Lucchesi
444b0f0f62
[Misc][Docs] Raise error when flashinfer is not installed and VLLM_ATTENTION_BACKEND is set ( #12513 )
...
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-02-24 10:43:21 -05:00
Zhonghua Deng
ccc00515fd
[BugFix] Illegal memory access for MoE On H20 ( #13693 )
2025-02-24 07:37:32 -08:00
Jongseok Park
781096e385
Expert Parallelism (EP) Support for DeepSeek V2 ( #12583 )
2025-02-24 07:33:20 -08:00
Roger Meier
7940d8a6a7
[CI/Build] add python-json-logger to requirements-common ( #12842 )
2025-02-24 06:10:33 -08:00
Roger Meier
c0e3ecd6d2
[Bugfix] fix(logging): add missing opening square bracket ( #13011 )
2025-02-24 06:10:25 -08:00
Mengqing Cao
23eca9cf68
[model][refactor] remove cuda hard code in models and layers ( #13658 )
2025-02-24 06:10:14 -08:00
Roger Wang
437b76ff59
[V1][Core] Fix memory issue with logits & sampling ( #13721 )
2025-02-24 06:10:06 -08:00
Kevin H. Luu
f90a375593
[ci] Add logic to change model to S3 path only when S3 CI env var is on ( #13727 )
...
Signed-off-by: <>
Co-authored-by: EC2 Default User <ec2-user@ip-172-31-63-253.us-west-2.compute.internal>
2025-02-24 06:32:11 +00:00
Huy Do
e7ef74e26e
Fix some issues with benchmark data output ( #13641 )
...
Signed-off-by: Huy Do <huydhn@gmail.com>
2025-02-24 10:23:18 +08:00
Nick Hill
cbae7af552
[V1][BugFix] Fix engine core client shutdown hangs ( #13298 )
...
Even though ZMQ context.destroy() is meant to close open sockets before terminating the context, it appears to be necessary to do this explicitly or else it can hang in the context.term() method.
Close zmq sockets explicitly before terminating context, make shutdown of client resource more robust, shut down engine core process prior to terminating zmq context.
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-02-23 13:07:43 -08:00
youkaichao
eb24dc4a45
[v1] torchrun compatibility ( #13642 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-02-23 22:47:24 +08:00
Roger Wang
9bebc9512f
[Misc] Deprecate --dataset from benchmark_serving.py ( #13708 )
...
Signed-off-by: Roger Wang <ywang@roblox.com>
2025-02-23 13:32:20 +00:00
Nick Hill
5a2ba16f5c
[Core][Distributed] Use IPC (domain socket) ZMQ socket for local comms ( #13688 )
2025-02-23 02:54:29 -08:00
