38 Commits
Author SHA1 Message Date
e711723352 [ROCm] gfx1250 optimizations and model enablement (#58800)
Signed-off-by: jpvillam <juan.villamizar@amd.com>
Signed-off-by: Jaden Mathias <jaden.mathias@amd.com>
Signed-off-by: Juan Villamizar <jpvillam@amd.com>
Signed-off-by: jpvillam <jpvillam@amd.com>
Signed-off-by: Omar Muhammad <omar.muhammad@amd.com>
Signed-off-by: Daniel <danichan@amd.com>
Signed-off-by: Juan Villamizar <100237675+jpvillam-amd@users.noreply.github.com>
Co-authored-by: Jaden Mathias <jaden.mathias@amd.com>
Co-authored-by: jpvillam <jpvillam@amd.com>
Co-authored-by: Omar Muhammad <omar.muhammad@amd.com>
Co-authored-by: Daniel <danichan@amd.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Daniel Chan <Daniel.Chan@amd.com>
2026-10-15 14:51:57 -07:00
Ilya Markov b3ee560ae8 [Bugfix][MoE] Apply expert_map remapping for CUTLASS FP4 MOE expert parallel (#59042)
Signed-off-by: Markov Ilya <markovilya197@gmail.com>
2026-10-12 10:02:56 -04:00
2d69083c4a [ROCm][MXFP4] Align the AITER W4A4 MoE intermediate size to 128 (#55104)
Signed-off-by: xiaofei.zheng <xiaofei.zheng@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Fangzhou Ai <31551580+Fangzhou-Ai@users.noreply.github.com>
2026-10-10 11:14:01 +08:00
Misha GoinandClaude 30c7405890 [MoE] MXFP4 oracle: add CUTLASS W4A4 backend and BF16 activation fallback (#60079)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-10-08 11:39:09 -07:00
4c4003bb5f [Bugfix] Bind routed-experts capture to the MoE layer, not the kernel (#59455)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-02 15:50:38 +00:00
Harry MellorandClaude Opus 5.5 fc2c801ad9 Disable mypy arg-type and assignment checks in tests (#59428)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 15:18:50 +00:00
31afa4f1bb [ROCm] Bump AITER to v0.1.23 (#58867)
Signed-off-by: fai <fangzhouai@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-09-27 19:04:58 -05:00
Yongye ZhuandClaude Opus 5.5 378504a544 [MoE] Defer the TRTLLM-Gen top-k finalize on the modular path (#58635)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-25 15:38:29 +08:00
Andreas KaratzasandOpenAI Codex 12972ae40b [Bugfix][ROCm] Reject unsupported EP for monolithic AITER MXFP4 MoE (#57866)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-09-21 15:30:21 -05:00
Harry MellorandClaude Opus 5 8c1557a79c Add pydocstyle to the ruff rules (#52136)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Harry Mellor <hej.mellor@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-16 16:44:29 +00:00
afriedriandAndreas Karatzas dc9114b201 [ROCm][MoE] Split AITER CK and Triton MXFP4 W4A16 into separate backends (#50622)
Signed-off-by: afriedri <afriedri@amd.com>
Signed-off-by: Andy Friedrich <afriedri@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-08-31 23:14:14 -05:00
xuebwang-amd c676232313 [Bugfix][Quantization] Fix OCP MX MoE emulation silently skipping mxfp6 activation QDQ (#52704)
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
2026-08-19 11:29:29 -05:00
Micah Williamson 8878ebd8fd [ROCm][CI] Expand AITER W4A4 MoE Coverage (#52647)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
2026-08-17 15:46:22 -05:00
Gabriel Wu 97388c44f9 [Bugfix] Make DSV4 sparse MLA work end-to-end for plain decode, MTP, and DSpark (#51538) 2026-08-15 07:01:32 -07:00
Fangzhou Ai 1044d19998 [ROCm][DSV4] Preserve native MXFP4 TP8 shard allocation (#51473)
Signed-off-by: Fangzhou Ai <fangzhou.ai@amd.com>
2026-08-10 23:57:27 -07:00
Jinzhen LinandOpenAI Codex fcde8e1460 [Refactor] refactor humming linear and moe backends to use explicit layer configs (#49610)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-08-07 10:03:19 -07:00
Gabriel WuandYongye Zhu 2e35c529b8 [Bugfix][Quantization] Fix MXFP4 conversion for FlashInfer CUTLASS (#51038)
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
2026-08-05 23:19:22 -07:00
Andreas Karatzas e279f71583 [ROCm][Test] Fix AITER MXFP4 oracle contract (#50728)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-08-03 20:53:18 +00:00
33fe71a4d3 [AMD] Revert Mxfp4MoeBackend.TRITON_UNFUSED fallback (#46491)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Co-authored-by: Felix Marty <Felix.Marty@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-07-27 22:31:23 -05:00
xuebwang-amd f12b80c6ef [ROCm][Bugfix] Fix GPT-OSS Quark MXFP4 MoE loading - emulation buffer not block-aligned (#43979)
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
2026-07-18 03:49:41 +00:00
6e073440b1 [ROCm][CI] Remove mxfp4 test skips after amd-quark 0.12 release (#47330)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: fxmarty-amd <felmarty@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-07-15 01:25:05 +00:00
Carl Persson 4a6bf3c77f [ROCm][CI] Fix Kernels and Kernels attention test failures (#47519)
Signed-off-by: Carl Persson <carl.persson@amd.com>
2026-07-04 15:59:51 -05:00
xiaolinchen 35e3850fa9 [Bugfix][Test] Fix test_flashinfer_cutlass_mxfp4_fused_moe on sm90 (stale weight/scale interleave) (#46915)
Signed-off-by: wentian-byte <2990624738@qq.com>
2026-06-27 14:30:10 -04:00
Divakar Verma 00e045b7c7 [ROCm][CI TG] refactor and fix deepep_moe test group (#46758)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
2026-06-27 10:45:23 +08:00
Micah Williamson 156b12667c [ROCm][CI] Skip Quark mxfp4 tests unless Quark version is compatible with Torch version (#46431)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
2026-06-23 22:26:39 +08:00
Matt 50241602fd [Hardware][AMD][CI] Fix gfx942 Kernels MoE test group (#46298)
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
2026-06-21 16:45:37 -05:00
bnellnm dc68bd8c41 [MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)
Signed-off-by: Bill Nell <bnell@redhat.com>
2026-06-08 10:42:58 -04:00
Bowen Bao 1e9500410a [ROCm][Quantization][2/N] Refactor quark_moe w4a8 w/ oracle (#39136)
Signed-off-by: Bowen Bao <bowenbao@amd.com>
2026-05-04 19:50:38 -07:00
bai 191e3fdaa1 Update flashinfer to 0.6.8 (#39959)
Signed-off-by: bai <v@gor.io>
2026-04-20 10:37:23 -07:00
Yongye ZhuandClaude Opus 4.6 87bd91892f [MoE Refactor] Mxfp4 oracle rebased (#37128)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 03:37:04 +00:00
Kunshang Ji 53ec16a705 [Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
2026-03-12 07:57:47 -07:00
danisereb 0a6a3a1290 Add support for ModelOpt MXFP8 MoE models (#35986)
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
2026-03-08 13:00:05 -07:00
elvischenv 808d6fd7b9 Bump Flashinfer to v0.6.1 (#30993)
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
2026-01-21 08:49:50 -08:00
Roberto L. Castroandyoukaichao 4fa7ce46f3 [Feature] Add SM103 (Blackwell Ultra) Support to vLLM (#30484)
Signed-off-by: LopezCastroRoberto <robertol.c510@gmail.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
2025-12-12 19:34:23 -08:00
Cyrus Leung 5a87d8b9b1 [Deprecation] Remove deprecated plugin and compilation fields for v0.13 release (#30396)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-12-10 19:59:35 -08:00
jiahancandMichael Goin 41d3071918 [NVIDIA] [Perf] Update to leverage flashinfer trtllm FP4 MOE throughput kernel (#26714)
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
2025-10-16 16:20:25 -07:00
Harry Mellor 8fcaaf6a16 Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-12 09:51:31 -07:00
fxmarty-amd 41f1cf38f2 [Feature][OCP MX] Support mxfp6 and mixed mxfp6-mxfp4 (#21166) 2025-10-07 09:35:26 -04:00