Commit Graph
13746 Commits
Author SHA1 Message Date
Gregory Shtrasberg f867dfcb29 ROCm 7.2 and disabled prebuild kernels for aiter. Added ROCm7.2 required libs to build aotriton; Use the new base image for this release
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2026-02-23 17:15:20 +00:00
Gregory Shtrasberg 59916839c9 Merge ROCm:upstream_fp8_with_static_scales_gpt_oss (#30357)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2026-02-23 17:15:20 +00:00
Gregory Shtrasberg 45219818d0 Merge ROCm:rocm_dsfp4_moe_shuffle (#34192)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2026-02-20 16:10:16 +00:00
9e9432ac96 [ROCm][Quantization] GPT_OSS in amd-quark format model loading and emulations (#29008)
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
2026-02-20 16:10:10 +00:00
Gregory Shtrasberg dadbceb1d9 Merge ROCm:rocm_defaults (#33271)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2026-02-20 16:09:17 +00:00
Gregory ShtrasbergandGregory Shtrasberg 830de08dc4 [Feature] Warn about unrecognized environment variables (#33581)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2026-02-11 16:20:24 +00:00
Seiji Eicherandkhluu c44d0c6d66 Patch protobuf for CVE-2026-0994 (#34253)
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
(cherry picked from commit 5045d5c983)
v0.16.0rc2
2026-02-11 02:33:40 -08:00
Kunshang Jiandkhluu 83db96d8cd [XPU][9/N] clean up existing ipex code/doc (#34111)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
(cherry picked from commit cb9574eb85)
2026-02-11 02:33:27 -08:00
zofiaandkhluu dbfb79fe45 [XPU][7/N] enable xpu fp8 moe (#34202)
Signed-off-by: Zhu, Zufang <zufang.zhu@intel.com>
(cherry picked from commit b482f71e9f)
2026-02-11 02:33:15 -08:00
Roger Wangandkhluu b2e1fc3589 [Bugfix][Core] Fix CPU memory leak from Request reference cycle in prefix caching (#34183)
Signed-off-by: Roger Wang <hey@rogerw.io>
(cherry picked from commit 8a5e0e2b2b)
2026-02-11 02:33:04 -08:00
Gregory Shtrasbergandkhluu 55a1baebc5 [Bugfix][ROCm][GPT-OSS] Use old triton_kernels implementation on ROCm if the new API is not available (#34153)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
(cherry picked from commit c60f8e3b49)
2026-02-11 02:32:52 -08:00
Charlie Fuandkhluu e1e9841631 [torch.compile][Fusion] Fix attention fusion pass removing kv_udpate op. (#33945)
Signed-off-by: charlifu <charlifu@amd.com>
(cherry picked from commit bb9f97308d)
2026-02-11 02:32:41 -08:00
zofiaandkhluu 5bd63387c3 [XPU][6/N] add xpu scaled_mm kernel (#34117)
Signed-off-by: Zhu, Zufang <zufang.zhu@intel.com>
(cherry picked from commit 9bdb06b436)
2026-02-11 02:32:27 -08:00
wang.yuqiandGitHub 22b64948f6 [Frontend][last/5] Make pooling entrypoints request schema consensus. (#31127)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
v0.16.0rc1
2026-02-09 06:42:38 +00:00
7c233dbb36 [Tiny] Rename encoder budget file to more specific name (#34103)
Signed-off-by: Reagan Lee <“reaganjlee@gmail.com”>
Co-authored-by: Reagan Lee <“reaganjlee@gmail.com”>
2026-02-09 03:48:19 +00:00
a75a5b54c7 [bug-fix] supported_tasks is breaking backward compatibility at init_app_state (#34027)
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: kourosh hakhamaneshi <31483498+kouroshHakha@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2026-02-09 09:46:46 +08:00
Andrey TalmanandGitHub f97ca67176 [Release 2.10] Update to Torch 2.10 - final release (#30525) 2026-02-08 13:51:09 -08:00
daniserebandGitHub 084aa19f02 Add support for ModelOpt MXFP8 dense models (#33786)
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
2026-02-08 11:16:48 -08:00
navmarri14andGitHub 1ecfabe525 glm 4.6 fused tuned inference config for B200 (#32958) 2026-02-08 18:55:47 +00:00
Richard ZouandGitHub 4df841fe75 [torch.compile] Add an option to force-enable the MOE cold start optimization (#33735)
Signed-off-by: Richard Zou <zou3519@gmail.com>
2026-02-08 18:42:56 +00:00
a263aa6140 [BugFix] Change support no act and mul for marlin (#34088)
Signed-off-by: Tomer Natan <tbarnatan@computelab-frontend-8.nvidia.com>
Co-authored-by: Tomer Natan <tbarnatan@computelab-frontend-8.nvidia.com>
2026-02-08 17:18:22 +00:00
aabbccddwasdandGitHub 179ae7da8f [Revert] Fix performance regression for GLM-4.7-GPTQ decode and MTP acceptance rate (#33771)
Signed-off-by: aabbccddwasd <aabbccddwasd@qq.com>
2026-02-08 08:13:24 -08:00
Reagan LeeGitHubReagan Leegemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
c4df59ad43 Add embedding input functionality for disabled modalities [remake] (#32493)
Signed-off-by: Reagan Lee <“reaganjlee@gmail.com”>
Signed-off-by: Reagan Lee <reaganjlee@gmail.com>
Signed-off-by: Reagan Lee <96998476+reaganjlee@users.noreply.github.com>
Co-authored-by: Reagan Lee <“reaganjlee@gmail.com”>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-02-08 04:57:16 -08:00
TJianandGitHub 785cf28fff [ROCm] [CI] Reduce Resource of two test groups (#34059)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
2026-02-08 15:17:26 +08:00
Nick HillandGitHub a96197f564 [Perf] Simplify DeepseekV32 tokenizer, ensure fast detokenization used (#33855)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
2026-02-08 07:16:34 +00:00
Andreas KaratzasandGitHub ab10d79855 [ROCm][Bugfix] fix act_quant_fusion module import error (#34069)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-02-07 19:21:12 -08:00
Cyrus LeungandGitHub 7fcb705b80 [CI/Build] Skip GCS test (#34057)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-02-07 08:52:38 -08:00
Cyrus LeungandGitHub b956cdf818 [Doc] Fix run_batch docs (#34056)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-02-07 06:18:16 -08:00
Hashem HashemiandGitHub ed17f54c8b Perf tuning and expansion of cases covered for wvSplitKrc (#33493)
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
2026-02-07 05:33:11 -08:00
Jiang WuandGitHub 860981d8d8 Make directory exist ok for ray spinning up multiple replicas on a single instance (#33604)
Signed-off-by: Jiang Wu <jwu@cclgroup.com>
2026-02-07 05:30:49 -08:00
52181baaea Update DeepGEMM version pin in Dockerfile to match #32479 (#33935)
Signed-off-by: Zifei Tong <zifeitong@gmail.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
2026-02-07 05:30:22 -08:00
Rohan PotdarandGitHub de3869bb4d move checks out of unified_kv_cache_update custom op (#33943)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
2026-02-07 05:30:09 -08:00
whxandGitHub ce9b3cd3e9 [PluggableLayer][3/N] Apply PluggableLayer to mamba layers. (#33660)
Signed-off-by: whx-sjtu <2952154980@qq.com>
2026-02-07 05:26:05 -08:00
Jee Jee LiandGitHub db4ede9743 [Model] Enable Step3p5ForCausalLM testing (#33755)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2026-02-07 05:25:24 -08:00
2cb2340f7a [Frontend]Add support for transcriptions and translations to run_batch (#33934)
Signed-off-by: Pooya Davoodi <pooya.davoodi@parasail.io>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2026-02-07 05:24:57 -08:00
TundeAtSNGitHubgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
4df44c16ba Enable Eagle3 speculative decoding for Mistral3ForConditionalGeneration to support eagle3 (#33939)
Signed-off-by: Akintunde Oladipo <akintunde.oladipo@servicenow.com>
Signed-off-by: TundeAtSN <akintunde.oladipo@servicenow.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-02-07 05:24:52 -08:00
Richard ZouandGitHub 81fe69cae5 [torch.compile] Stop compiling identical artifacts (#34003)
Signed-off-by: Richard Zou <zou3519@gmail.com>
2026-02-07 05:24:48 -08:00
dd6a6e1190 [Kernel] Add KernelConfig flag to enable/disable FlashInfer autotune (#34006)
Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
2026-02-07 05:24:44 -08:00
Cyrus LeungandGitHub edb359cce4 [Renderer] Define render_cmpl and render_chat (#34039)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-02-07 05:24:40 -08:00
6ed5eda300 [CI][Build] Pin grpcio-tools==1.78.0 (#34048)
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2026-02-07 05:24:35 -08:00
Cyrus LeungandGitHub 11a4c9d30d [Misc] Simplify get_max_tokens (#34036)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-02-07 00:59:49 -08:00
lukecandGitHub 15a0b9e570 Fix spelling errors (#33978) 2026-02-06 23:58:50 -08:00
Andreas KaratzasandGitHub c490d8cc73 [ROCm][CI] Pinning lm-eval version to resolve multi-modal small eval bug (#34038)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-02-06 22:21:08 -08:00
Cyrus LeungandGitHub 48312e579a [Misc] Make PlaceholderRange.get_num_embeds a method (#34035)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-02-07 05:30:17 +00:00
VelandGitHub bc32444b23 [Kernel] Add enable_sm120_or_later for SM121 (DGX Spark) CUTLASS support (#33517)
Signed-off-by: code4me2 <velvetmoon222999@gmail.com>
2026-02-06 20:28:01 -08:00
Wentao YeandGitHub 18e8545297 [Revert] Add util handle_deprecated back (#33998)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2026-02-07 04:14:45 +00:00
果冻虾仁andGitHub 6f7adc533a fix description in plugin_system.md (#33999) 2026-02-06 19:37:02 -08:00
Nick HillandGitHub 40218a82ba [ModelRunner V2] Revert token rank comparison difference for now (#34017)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
2026-02-07 11:11:05 +08:00
1c3b22058f [Misc] Add backward-compatible import aliases for renamed translations module (#34015)
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-07 11:01:41 +08:00
Xin YangandGitHub 3920cafdd6 [Bugfix] Fix _fused_moe_lora_expand signature mismatch (#33821)
Signed-off-by: Xin Yang <xyangx@amazon.com>
2026-02-07 10:45:59 +08:00