Commit Graph
46 Commits
Author SHA1 Message Date
Max HuandMax Hu d462dee37d [Bugfix][Triton] Make fp8_min/fp8_max constexpr in _quantize_pad_fp8_kernel (#51872)
Signed-off-by: Max Hu <maxhu@nvidia.com>
Co-authored-by: Max Hu <maxhu@nvidia.com>
2026-08-12 03:09:54 +00:00
Chaojun ZhangandKunshang Ji 482cfc20f0 [XPU] Unify XPU RMSNorm kernels with vllm_c and drop redundant XPU-specific implementation (#46981)
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
2026-07-31 17:28:18 +08:00
Shangdi YuandOpenAI Codex 45b60e3914 [Kernel][Helion] Disable unsafe B200 RMS reduction warp specialization (#50345)
Signed-off-by: Shangdi Yu <shangdiy@meta.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-07-30 20:37:52 +00:00
BadrBasowid 59e831c09a [Compilation]Fuse Transformers Residual Add + RMSNorm (#48757)
Signed-off-by: BadrBasowid <badr.basowid@gmail.com>
2026-07-30 13:46:36 +00:00
72297d859b [XPU] Route weightless RMSNorm to _C dispatch (#47121)
Signed-off-by: Yintong Lu <yintong.lu@intel.com>
Co-authored-by: Yongqi Wang <yongqi.wang@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
2026-07-29 18:59:58 +08:00
Andreas Karatzas 49f31d7cee [ROCm] Make vllm_c RMSNorm output contiguous (#49913)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-07-26 23:59:14 -05:00
Shangdi YuandClaude Opus 4.8 c9be3a8aa1 [Kernel][Helion] Disable warp specialization in rms_norm_per_block_quant B200 configs (#48797)
Signed-off-by: Shangdi Yu <shangdiy@meta.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-17 21:39:09 +00:00
Shangdi Yu efa2e424f6 [Helion] Fix degenerate scale_ub in kernel input generators (#48868)
Signed-off-by: Shangdi Yu <shangdiy@meta.com>
2026-07-16 19:57:45 +00:00
Xiaohong (Sean) Chen 6036bf110a [Kernel][Helion] Add Helion kernel benchmark script (#48512)
Signed-off-by: Sean Chen <seachen@redhat.com>
2026-07-15 15:43:06 +00:00
Xiaohong (Sean) Chen 2fa63e0fff [Kernel][Helion] Helion kernel lazy registration (#48264)
Signed-off-by: Sean Chen <seachen@redhat.com>
2026-07-15 15:42:46 +00:00
Xiaohong (Sean) ChenAndreas Karatzasmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
9fde043f54 [Kernel][Helion][1/N] Add Helion kernel for silu_and_mul_per_block_quant (#43994)
Signed-off-by: Sean Chen <seachen@redhat.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-07-07 00:19:01 +08:00
Wentao Ye b1c6dba558 [Refactor] Remove multiple dead code (#47329)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2026-07-06 07:54:08 -07:00
zofiaandKunshang Ji 72f639927f [XPU] [RMSNorm] revert weightless change on xpu (#46987)
Signed-off-by: Zhu, Zufang <zufang.zhu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
2026-06-29 19:03:06 +00:00
Xiaohong (Sean) Chen 49e28e8e91 [Kernel][Helion][1/N] Add Helion kernel for fused_qk_norm_rope (#44010)
Signed-off-by: Sean Chen <seachen@redhat.com>
2026-06-29 22:54:15 +08:00
cyq e06a83445c [Bugfix] Normalize slashes in Helion GPU names (#46101)
Signed-off-by: cyq <15000851237@163.com>
2026-06-24 18:22:49 -05:00
Xiaohong (Sean) ChenandYanan Cao 46f74e144b [Kernel][Helion][1/N] Add Helion kernel for rms_norm_dynamic_per_token_quant (#34432)
Signed-off-by: Sean Chen <seachen@redhat.com>
Co-authored-by: Yanan Cao <gmagogsfm@gmail.com>
2026-06-17 23:03:54 +08:00
arghyadeep sarkar 93bbe94d3a [Kernel] Add weightless RMSNorm CUDA kernels for has_weight=False (#41430) (#44109)
Signed-off-by: hello-args <args.sarkar@gmail.com>
2026-06-16 23:45:55 -07:00
Xiaohong (Sean) ChenandYanan Cao ce3ef17bec [Kernel][Helion][1/N] Add Helion kernel for rms_norm_per_block_quant (#36895)
Signed-off-by: Sean Chen <seachen@redhat.com>
Co-authored-by: Yanan Cao <gmagogsfm@gmail.com>
2026-06-16 22:09:52 +08:00
Xiaohong (Sean) ChenandYanan Cao 272c16953e [Kernel][Helion][1/N] Add Helion kernel for dynamic_per_token_scaled_fp8_quant (#33790)
Signed-off-by: Sean Chen <seachen@redhat.com>
Co-authored-by: Yanan Cao <gmagogsfm@gmail.com>
2026-06-12 12:50:06 -04:00
Xiaohong (Sean) ChenYanan Caomergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2ec6594db9 [Kernel][Helion][1/N] Add Helion kernel for per_token_group_fp8_quant (#36902)
Signed-off-by: Sean Chen <seachen@redhat.com>
Co-authored-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-11 08:59:08 -07:00
Andreas Karatzas d28bdf9344 [ROCm][CI] Fix ROCm LoRA Transformers fallback with full CUDA graphs (#41577)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-05-23 04:31:32 +00:00
Yanan CaoandClaude Sonnet 4 0b99971352 [Kernel][Helion] Optimize Helion config parsing latency (#40850)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Sonnet 4 <noreply@anthropic.com>
2026-05-07 20:27:34 -07:00
Luka Govedič d58c42e19c [vLLM IR] 2/N fused_add_rms_norm and maybe_inplace overload (#36823)
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
2026-05-01 23:41:15 -04:00
Zhanda ZhuandYubo Gao 5d5c776444 [Perf] FP8 FlashInfer Attn for ViT (#38065)
Signed-off-by: Zhanda Zhu <zhandazhu@gmail.com>
Co-authored-by: Yubo Gao <ybgao-nvidia@users.noreply.github.com>
2026-04-27 13:44:15 +08:00
Yanan CaoandClaude Sonnet 4 5cdddddd4a [Kernel] [Helion] Force disable HOP path due to performance regression (#40171)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Sonnet 4 <noreply@anthropic.com>
2026-04-17 17:36:49 -04:00
Yanan CaoandClaude Opus 4.6 edc3648966 [Kernel][Helion] Fix inductor fusion of Helion HOP (#39944)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-16 04:41:26 -07:00
Jiangyun ZhuandLuka Govedič 8060bb0333 [vLLM IR] rework gemma_rms_norm (#39014)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
2026-04-07 01:37:00 -07:00
Robert Shaw 7d266abb22 Revert "[vLLM IR] gemma_rms_norm" (#38998) 2026-04-04 17:48:08 -04:00
Xiaoshuang Wang 156405d243 [vLLM IR] gemma_rms_norm (#38780)
Signed-off-by: Icey <1790571317@qq.com>
2026-04-04 13:55:52 -04:00
Yanan CaoandClaude Sonnet 4 73f48ce559 [Kernel] [Helion] Use warning_once in get_gpu_name to prevent log spam (#38743)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Sonnet 4 <noreply@anthropic.com>
2026-04-01 21:30:31 -07:00
40bb175027 [vLLM IR] 1/N Implement IR skeleton and rms_norm op (#33825)
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Xinyu Chen <xinyu1.chen@intel.com>
Signed-off-by: chzhang <chaojun.zhang@intel.com>
Signed-off-by: Luka Govedic <luka.govedic@gmail.com>
Co-authored-by: Xinyu Chen <xinyu1.chen@intel.com>
Co-authored-by: Chaojun Zhang <chaojun.zhang@intel.com>
Co-authored-by: Luka Govedič <ProExpertProg@h100-01.nemg-001.lab.rdu2.dc.redhat.com>
2026-03-31 22:15:05 -04:00
Yanan CaoandClaude Sonnet 4 cc671cb110 [Kernel] [Helion] [17/N] Add Helion kernel torch.compile support (#38592)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Sonnet 4 <noreply@anthropic.com>
2026-03-31 17:06:42 -04:00
Yanan CaoandClaude Opus 4.6 ff9fbc9aff [Kernel][Helion] [16/N] Refactor register_kernel API to be more Dynamo-friendly (#36705)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-18 01:23:35 +00:00
Yanan CaoandClaude Opus 4.6 584a3f56de [Kernel][Helion][13/N] Force static_shapes=False in helion register (#36677)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-12 05:35:29 +00:00
Yanan CaoandClaude Opus 4.6 cf632499ee [Kernel] [Helion] [15/N] Split config files into per-platform files (#36698)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-11 17:25:29 -04:00
Yanan CaoandClaude Opus 4.6 0ce21c46a0 [Kernel] [Helion] [14/N] Set autotune_ignore_errors=True during autotuning (#36683)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-11 17:25:04 -04:00
Yanan Cao b0651021e5 [Kernel] [Helion] [11/N] Retune configs for silu_mul_fp8 (#36062) 2026-03-04 21:25:59 -08:00
Yanan Cao 9098ce690c [Kernel] [Helion] [7/N] Use HOP to represent Helion Kernel call to enable fx tracing and pattern matching (#34390)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
2026-02-27 09:21:35 -08:00
Yanan CaoandClaude Opus 4.6 9d7577b2bd [Kernel] [Helion] [9/N] Canonicalize GPU variant names to base model names (#34928)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-20 19:55:51 -08:00
Yanan Cao a6d0299c75 [Kernel] [Helion] [6/N] Add num_tokens dimension to silu_mul autotuning and dispatching (#34185)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
2026-02-20 08:36:51 -08:00
Andreas Karatzas f13e86d8dd [Kernels] Fix Helion GPU utils to use platform-agnostic device name API (#34537)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-02-14 20:29:23 -08:00
Yanan Cao de13dd781f [Kernel] [Helion] [5/N] Add Helion Autotuning infrastructure (#34025)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
2026-02-12 18:21:05 -08:00
Yanan Cao 96161fe978 [Kernel] [Helion] [4/N] Add silu_mul_fp8 Helion kernel (#33373)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
2026-02-12 18:13:12 -08:00
Yanan Cao d5c41db35b [Kernel] [Helion] [3/N] Helion kernel registry (#33203)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
2026-01-31 15:38:46 +08:00
Yanan Cao 8ecd213c0b [Kernel] [Helion] [2/N] Helion kernel wrapper (#32964)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
2026-01-31 12:53:01 +08:00
Yanan Cao 6c1f9e4c18 [Kernel] [Helion] [1/N] Add Helion ConfigManager (#32740)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
2026-01-30 12:19:19 -05:00