minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
18,248 Commits 2 Branches 0 Tags
45b511b2efa0faa2ed5893fcd0d9ee61789c1910
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
YC Yen-Ching Tseng ce66ba2844 [AMD] Fix AITER FP8-Q unified-attention Test (#39360) 2026-09-13 23:35:24 -07:00
YC Yen-Ching TsengandChen f618022b73 [AMD][CI] Temporarily pause MI355X disaggregated nightly (#39044) 
Co-authored-by: Chen <bingxche@amd.com>
 2026-09-11 15:19:24 +08:00
YC Yen-Ching Tseng 6b2e13bcb0 [AMD] Fix the diffusion perf fixture lookup (#38686) 2026-09-10 00:07:08 -07:00
YC Yen-Ching TsengandChen Bingxu 708f51e44b [AMD][CI] Make ROCm 10 the Default for AMD PR and Nightly Tests (#38659) 
Co-authored-by: Chen Bingxu <bingxche@amd.com>
 2026-09-09 17:28:20 +08:00
YC Yen-Ching TsengandChen 4c3d47f1df [AMD] Copy MoE weight views before H2D in slow-loading nightlies (#38456) 
Co-authored-by: Chen <bingxche@amd.com>
 2026-09-08 16:19:28 +08:00
YC Yen-Ching TsengandChen f59a4840c5 [AMD][CI] Correct MI355X Slurm exclude node (#37779) 
Co-authored-by: Chen <bingxche@amd.com>
 2026-09-03 18:32:44 +08:00
YC Yen-Ching TsengandPhil Li 1fb85053e7 [AMD][Diffusion] Migrate FlyDSL fused norm kernels to the v0.3.0 stable API (#36349) 
Co-authored-by: Phil Li <haicli@amd.com>
 2026-09-02 23:03:08 -07:00
YC Yen-Ching TsengandChen 99b9109553 [AMD] Run ROCm 7.0 shadow tests every two days- #37582 (#37586) 
Co-authored-by: Chen <bingxche@amd.com>
 2026-09-02 17:51:16 +08:00
YC Yen-Ching TsengandChen 0157f1f552 [AMD][CI] Exclude unavailable MI355X nodes and skip 4N nightly (#37518) 
Co-authored-by: Chen <bingxche@amd.com>
 2026-09-02 11:06:54 +08:00
YC Yen-Ching TsengandChen 3103bc7462 [AMD][CI] Add daily ROCm 10 and ROCm 7.2 test coverage (#37409) 
Co-authored-by: Chen <bingxche@amd.com>
 2026-09-01 19:23:19 +08:00
YC Yen-Ching Tseng b425897366 [AMD] Gate the aiter memory-reserve exemption behind an env var (#37242) 2026-09-01 03:46:15 -07:00
YC Yen-Ching Tseng 0674be736c [AMD] build gfx1250 release image from main (#37225) 2026-08-31 17:04:04 +08:00
+1
YC Yen-Ching TsengHAIKaowunhuangThomas WangXinyi SongLin, SogakkBingxu Chensogalin_codegenThomas Wang
 		3865efc9f7 [AMD] support gfx1250 on ROCM 10 (#36871) 
Co-authored-by: HAI <hixiao@gmail.com>
Co-authored-by: Kao <akao@amd.com>
Co-authored-by: wunhuang <wunhuang@amd.com>
Co-authored-by: Thomas Wang <1am9trash@gmail.com>
Co-authored-by: Xinyi Song <86638975+RolaoDenthu@users.noreply.github.com>
Co-authored-by: Lin, Soga <soga.lin@amd.com>
Co-authored-by: kk <43161300+kkHuang-amd@users.noreply.github.com>
Co-authored-by: Bingxu Chen <bingxche@amd.com>
Co-authored-by: sogalin_codegen <39478626+sogalin@users.noreply.github.com>
Co-authored-by: Thomas Wang <thomawan@amd.com>
 2026-08-31 01:19:11 -07:00
YC Yen-Ching TsengandAlex Nails 5972211977 [AMD] Fix the QuickReduce bf16 cast failing to build for CDNA (#37132) 
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
 2026-08-30 20:57:29 -07:00
YC Yen-Ching Tseng c7879af887 [AMD] release rocm10 image for gfx1250 from amd_helios (#36892) 2026-08-28 12:00:25 -07:00
YC Yen-Ching Tseng 7ba3430365 Fix Grok-2 nightly: derive image-understanding capability from is_multimodal (#33730) 2026-08-19 23:56:51 -07:00
YC Yen-Ching Tseng f7101b0ae6 [AMD] MiniMax-M3 : Fuse QKV+index proj for block-fp8 (#32099) 2026-08-18 03:01:01 -07:00
YC Yen-Ching Tsengyctseng0211Chen
 		00bdafe944 [AMD][CI] Swap the AMD PR gate to ROCm 7.2 and demote ROCm 7.0 to a daily shadow (#34204) 
Co-authored-by: yctseng0211 <yctseng@smci355-ccs-aus-m12-17.cs-aus.dcgpu>
Co-authored-by: Chen <bingxche@amd.com>
 2026-08-12 03:31:03 -07:00
YC Yen-Ching Tseng b8140f36ea Fix lint error (#33830) 2026-08-06 00:53:40 -07:00
YC Yen-Ching TsengandHaiShaw cf7923615c [AMD] Gate DFLASH non-greedy verify on the target-only kernel being registered (#33694) 
Co-authored-by: HaiShaw <hixiao@gmail.com>
 2026-08-06 00:10:22 -07:00
YC Yen-Ching TsengandChen e675c7226a [AMD]Stage MI355X nightly by node count (#33774) 
Co-authored-by: Chen <bingxche@amd.com>
 2026-08-06 09:04:29 +08:00
YC Yen-Ching TsengandChen 8279702e0b [AMD] Stop publishing the K3 MI35X nightly image (#33689) 
Co-authored-by: Chen <bingxche@amd.com>
 2026-08-05 17:53:23 +08:00
YC Yen-Ching Tseng eaf5c29cc5 [AMD] Enable block-fp8 + quick INT4 all-reduce in MiniMax-M3 MI35x nightly Test (#33402) 2026-08-04 01:55:06 -07:00
YC Yen-Ching Tseng 70cec31378 [AMD] Pin mem_fraction_static for the piecewise CUDA graph 1-GPU test on MI300 (#32862) 2026-07-31 14:56:30 -07:00
YC Yen-Ching Tseng fd86795107 [AMD] MiniMax-M3: opt-in custom/quick all-reduce on ROCm (#32230) 2026-07-30 02:56:07 -07:00
YC Yen-Ching Tseng 04d6fb4d6c [AMD] Minimax-M3 : unblock mxfp8 block convert on gfx950 (#32036) 2026-07-30 02:43:27 -07:00
YC Yen-Ching Tseng 68673fe6c5 [AMD] add Gemma3RMSNorm.forward_hip to unbreak ROCm (#32613) 2026-07-28 21:19:17 -07:00
YC Yen-Ching TsengbingxcheCursor
 		4fe8f5218d [AMD] Add Kimi K3 ROCm 7.2 nightly image (#32643) 
Co-authored-by: bingxche <bingxche@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-28 18:45:23 +08:00
YC Yen-Ching Tsengandbingxche 2b6e01c673 [AMD] Run AITER Scout on Saturdays (#32632) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-07-28 16:56:51 +08:00
YC Yen-Ching Tseng 1d0cd2e473 [AMD] Nightly Test Coverage - Minimax-M3-MXFP8 Accuracy Test (#30613) 2026-07-25 23:52:22 -07:00
YC Yen-Ching Tsengandbingxche 71fe649d68 [AMD] Register the Helios release workflow on main (#32069) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-07-22 21:14:21 +08:00
YC Yen-Ching Tsengandbingxche b6be150798 [AMD] Split ROCm 7.2 Stage-B large 1-GPU tests into three partitions (#31792) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-07-20 23:16:10 +08:00
YC Yen-Ching Tseng 377c93d54e [AMD] Gate TP4 o_proj/qkv CK block-FP8 GEMM shapes to Triton (ROCm 7.0 Qwen-3.5) (#30940) 2026-07-19 01:45:44 -07:00
YC Yen-Ching Tseng c68392c535 [AMD] Fix DeepSeek MLA prefill shape mismatch on HIP eager fallback (missing mha_companion_layers) (#31675) 2026-07-19 01:40:41 -07:00
YC Yen-Ching Tsengandbingxche 4d60c4540c [AMD] Skip AMD nightly local registry push (#31436) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-07-16 16:15:05 +08:00
YC Yen-Ching Tseng 8c5e0cee18 [AMD] Bump MoRI to f7e6ac6 to fix ROCm install_dependency build break (#31406) 2026-07-15 23:40:18 -07:00
YC Yen-Ching Tseng 14095ef78a [AMD] Disable CUDA IPC multimodal transport on ROCm in MMMU VLM tests (#31342) 2026-07-15 18:42:30 -07:00
YC Yen-Ching Tsengandkangwangamd a8b60433c2 [AMD] Fix DSV4 JIT build on rocm (#31131) 
Co-authored-by: kangwangamd <kangwang@amd.com>
 2026-07-15 09:58:12 -07:00
YC Yen-Ching Tseng 80965db8d3 [AMD] Pin cmake==4.3.4 in ROCm Dockerfile to fix MoRI gtest_discover build break (#30942) 2026-07-12 18:20:17 -07:00
YC Yen-Ching Tseng fc378f843e [AMD] Temporarily reduce AMD scheduled test frequency to save resource (#30534) 2026-07-08 09:30:59 -07:00
YC Yen-Ching Tseng 669b4bc72b [AMD] Gate stage-c on stage-b-test-1-gpu-large-amd (#30496) 2026-07-08 15:41:21 +08:00
YC Yen-Ching Tsengandbingxche 9bf122a455 [AMD] Run MI355X disaggregation Nightly Test with runtime checkout code mechanism (#30386) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-07-08 09:27:49 +08:00
YC Yen-Ching Tseng 67697fb891 [AMD] Temporarily disabled: every-6-hours rocm 7.2 test (#30014) 2026-07-03 15:38:07 +08:00
YC Yen-Ching Tseng 05bc3f2aa7 [AMD] Gate broken CK block-FP8 GEMM shapes to aiter-triton-GEMM to fix ROCm 7.0 Qwen3.5 accuracy (#29918) 2026-07-02 18:18:37 -07:00
YC Yen-Ching Tseng 2a6e5c60fe [AMD] Rebalance stage-c-large-8-gpu-mi35x partitions to fix 60-min timeout (#29726) 2026-07-01 08:17:00 -07:00
YC Yen-Ching Tseng 308d89e042 [AMD] Split qwen3.5 triton DCP test into its own nightly job (#29409) 2026-07-01 00:39:39 -07:00
YC Yen-Ching Tsengandbingxche c70cc96905 [AMD] Stop rocm720 pr auto-runs (#29768) 
Co-authored-by: bingxche <bingxche@users.noreply.github.com>
 2026-06-30 23:58:25 +08:00
YC Yen-Ching Tsengandbingxche f2756f53f3 [AMD] Update AMD local registry address (#29765) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-06-30 23:40:00 +08:00
YC Yen-Ching Tseng 7d9116d9d7 Fix test_type_based_dispatcher after TokenizedGenerateReqInput field changes (#29376) 2026-06-29 22:22:22 -07:00
YC Yen-Ching Tsengandbingxche 5169df70f6 [AMD] Sgl-data mount opt-in (#29661) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-06-29 22:11:37 +08:00
YC Yen-Ching Tseng 5eebb4b2e8 [AMD] Fix fused append+remap DeepEP equivalence test on aiter path (#29377) 2026-06-26 16:04:20 -07:00
YC Yen-Ching Tseng bc150173b2 [AMD] Fix stage-b-test-1-gpu-small-amd-nondeterministic timeout after VLM model swap (#29234) 2026-06-25 03:56:04 -07:00
YC Yen-Ching TsengbingxcheClaude Opus 4.8
 		b42c79c4eb [AMD] Fix AMD extra scheduled runs cancelling each other (#28989) 
Co-authored-by: bingxche <bingxche@amd.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-23 11:48:32 +08:00
YC Yen-Ching Tseng dd39ef6cec [AMD] Pin httpx>=0.25.0 to fix anthropic SDK socket_options error (#28869) 2026-06-22 07:25:22 -07:00
YC Yen-Ching Tseng 73448b0d70 [AMD] Temporarily disable deepseek V4 in AMD PR test (#28871) 2026-06-22 10:48:38 +08:00
YC Yen-Ching Tseng 3b5aae278e Fix EagleDraftExtendInput missing kv_indptr crash with triton/DP attention (#28221) 2026-06-17 14:54:33 -07:00
YC Yen-Ching Tseng 9b8c41171a [AMD] Fall back to layer_first layout for kernel write-back on ROCm (#28473) 2026-06-17 03:01:43 -07:00
YC Yen-Ching Tseng 102392df5b [AMD][Fix] Skip EPLB topk remap when global server args are unset (#28404) 2026-06-16 01:13:22 -07:00
YC Yen-Ching TsengbingxcheCursor
 		ed9024e09f [AMD] Fix AITER Scout workflow permissions (#28360) 
Co-authored-by: bingxche <bingxche@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-06-16 11:21:39 +08:00
YC Yen-Ching Tsengandbingxche 19e85868f6 [AMD] Point AITER scout at amd/aiter-ci (#28313) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-06-15 22:50:16 +08:00
YC Yen-Ching Tseng 17d8c5801d [AMD] Fix test_deepseek_r1_mxfp4_8gpu.py : disable async-assert probes on AMD CI (#27505) 2026-06-09 08:12:35 -07:00
YC Yen-Ching Tseng a26587dd4e [AMD][diffusion] Add FlyDSL fused normalization kernels for ROCm diffusion models optimization (#22786) 2026-06-08 02:42:39 -07:00
YC Yen-Ching TsengbingxcheCursor
 		66b932154f [AMD] fix(ci): run partition 3 of stage-c-test-large-8-gpu-amd (#27352) 
Co-authored-by: bingxche <bingxche@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-06-05 15:06:36 +08:00
YC Yen-Ching Tseng 69623f4b11 [AMD] Guard aiter greedy_sample OOB token id (fixes VLM MMMU CI) (#27247) 2026-06-04 12:53:58 -07:00
YC Yen-Ching Tseng ff93a576e5 [AMD] Minimax M25 : FP8 block-scale GEMM dispatch for ROCm 7.0 on gfx950 (#27111) 2026-06-04 00:41:42 -07:00
YC Yen-Ching TsengbingxcheCursor
 		04c16fc1e5 [AMD][CI] Remove transformers pin from GLM-5.x nightly jobs (#27232) 
Co-authored-by: bingxche <bingxche@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-06-04 14:34:07 +08:00
YC Yen-Ching Tseng 6dcd78a37f [AMD] Add MiniMax-M2.5 TP=4 nightly accuracy test for MI355X (#27126) 2026-06-03 22:17:40 -07:00
YC Yen-Ching Tseng d1bc06b63b [AMD] Disable AITER custom all-gather in DeepSeek-R1-MXFP4 8-GPU test (#27163) 2026-06-03 13:38:34 -07:00
YC Yen-Ching TsengCursor AgentBingxu ChenBingxu Chen
 		b14fba17d9 [AMD] make bypass-fastfail label also disable within-suite fast-fail (#26909) 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Bingxu Chen <Bingxu.Chen@amd.com>
Co-authored-by: Bingxu Chen <bingxche@amd.com>
 2026-06-01 16:17:59 +08:00
YC Yen-Ching Tseng f60710a1d7 [AMD] Fix stage-b-test-large-8-gpu-mi35x-disaggregation-amd : switch CACHE_HOST to a fresh path to fix "No space left on device" (#26905) 2026-06-01 16:00:58 +08:00
YC Yen-Ching Tseng 272066566f [AMD] Pin compressed-tensors<0.16.0 for srt_hip (fixes ROCm 7.2 nightly build) (#26591) 2026-05-29 11:34:45 +08:00
YC Yen-Ching Tseng 505f37a63d [AMD] force AITER checkout to bypass CSV CRLF/LF smudge dirty state (#26535) 2026-05-28 14:05:53 +08:00
YC Yen-Ching Tseng f32ca1e0e5 [AMD] AＭD CI - temporarily change to mi325 (#26443) 2026-05-27 13:55:03 +08:00
YC Yen-Ching Tseng d25a220fdb [AMD] Relaxing timeout for AMD CI (#26392) 2026-05-26 17:25:05 +08:00
YC Yen-Ching TsengCursor AgentBingxu Chenbingxche
 		8562d5ae94 [AMD] Relaxing Timeout for AMD stage-a (#25978) 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Bingxu Chen <Bingxu.Chen@amd.com>
Co-authored-by: bingxche <bingxche@amd.com>
 2026-05-21 17:32:51 +08:00
YC Yen-Ching Tseng 90efa9c83f [AMD] Fix AMD stage-a-test-small-1-gpu (#25932) 2026-05-20 20:51:49 -07:00
YC Yen-Ching Tseng 7c3f614e23 [AMD] Bump amd/Kimi-K2.5-MXFP4 revision to align with shared-experts fusion (#25740) 2026-05-18 22:47:05 -07:00
YC Yen-Ching Tseng 22bfae0d1d [AMD] Auto-fallback NSA indexer to page_size=1 when aiter preshuffle gluon kernel is unavailable (Deepseek v3.2) (#25205) 2026-05-14 00:01:56 -07:00
YC Yen-Ching Tseng cf92ccbf18 [AMD] Run jit kernel PR test through run_suite.py register mechanism (#24987) 2026-05-13 02:57:08 -07:00
YC Yen-Ching Tseng 72b266d59b [AMD] Disable unittest fail-fast for deepseekv4 perf test (#25039) 2026-05-12 22:47:31 -07:00
YC Yen-Ching Tseng 6b6963f426 [AMD] Update scripts/ci/amd/ensure_vram_clear.sh (#24586) 2026-05-11 18:47:09 +08:00
YC Yen-Ching Tseng 126a36a986 [AMD] VRAM cleanup step to AMD nightly test workflows (#24612) 2026-05-11 11:08:51 +08:00
YC Yen-Ching Tseng b35d14b64d [AMD] Retry logic for lmms-eval installation (#24615) 2026-05-11 10:55:24 +08:00
YC Yen-Ching Tseng e1150f66db [AMD][diffusion] Temporal-unfolded batched Conv2D for ROCm VAE decode (#22971) 2026-05-08 02:32:14 -07:00
YC Yen-Ching Tsengandbingxche c18879054f [AMD] Route PR multimodal tests to MI325 (#24614) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-05-07 23:26:05 +08:00
YC Yen-Ching Tseng 64613543ea [AMD] fix(docker): unbreak nightly when archive.ubuntu.com:80 is unreachable (#24407) 2026-05-05 00:39:14 -07:00
YC Yen-Ching Tsengandbingxche cf4f462094 [AMD] Nightly image release for deepseek v4 (#24155) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-04-30 23:49:13 +08:00
YC Yen-Ching Tseng 9e68c8527e [AMD] Update AMD Nightly Test checkout mechanism (#24112) 2026-04-30 11:36:18 +08:00
YC Yen-Ching Tsengandbingxche 155e333039 [AMD] Update AMD CI workflow concurrency group (#24065) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-04-29 22:39:18 +08:00
YC Yen-Ching Tseng adc59325bc [AMD] Optimize MiniMax-M2.5 - enable fused Triton kernel for FP8 KV cache write in aiter decode path (#23620) 2026-04-24 22:23:49 -07:00
YC Yen-Ching Tseng fb272d27db [AMD] Optimize MiniMax-M2.5 - use aiter biased_grouped_topk for sigmoid scoring in MoE routing (#23611) 2026-04-24 22:18:08 -07:00
YC Yen-Ching Tsengandbingxche b060a5ccfd [AMD] Fix nightly version tag selection (#23644) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-04-24 17:39:47 +08:00
YC Yen-Ching Tsengandbingxche 30909cbeeb [AMD] upd local registry address (#23607) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-04-24 12:07:09 +08:00
YC Yen-Ching Tseng 74fdf9cd77 [AMD] CI - Fix the cancelled guard to AMD CI (#23338) 2026-04-21 15:45:26 +08:00
YC Yen-Ching Tseng da62e90904 [AMD] Fix multimodal timeout issue : rocm7.2 PR Test (#23247) 2026-04-20 18:36:08 +08:00
YC Yen-Ching Tsengandbingxche cf4b84f839 [AMD] Update AMD workflow name (#23245) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-04-20 18:18:24 +08:00
YC Yen-Ching Tseng 32b7777f6c [AMD]Fix AMD multimodal-gen-test-2-gpu timeout by adding partition for standalone test (#23130) 2026-04-19 23:16:18 +08:00
YC Yen-Ching Tseng 5d4e899477 [AMD] Fix AMD Multimodal Test - skip nvfp4 tests (#23045) 2026-04-17 09:02:39 -07:00
YC Yen-Ching Tsengandbingxche f399997d2f [AMD] mirror nightly images to local registry and prefer LAN pulls (#23073) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-04-17 19:49:26 +08:00
YC Yen-Ching Tsengandbingxche 8c13295842 [AMD] fix AMD CI gate (#22974) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-04-17 18:32:26 +08:00