Commit Graph

2110 Commits

Author SHA1 Message Date
HAI
5c54ef0352 AMD/ROCm: update AITER repo to ROCm/aiter (#3747) 2025-02-21 00:18:08 -08:00
Shenggui Li
c6a4852136 [docs] added torch.compile cache to dpsk manual (#3737) 2025-02-21 00:11:40 -08:00
Trayvon Pan
4f678c87d8 docs: fix 404 link (#3588)
Co-authored-by: yqtianust <yqtian@ust.hk>
2025-02-20 15:15:57 -08:00
aoshen524
e79f7420be [Fix] Fix bugs and refactor codes in lora for better scalability. (#3652)
Co-authored-by: ShenAo1111 <1377693092@qq.com>
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
2025-02-20 11:51:57 -08:00
Baizhou Zhang
ac05310098 [Docs] Modify ep related server args and remove cublas part of deepseek (#3732) 2025-02-21 03:37:56 +08:00
chenxiaobing
d5d80ab477 [Bugfix] Fix scores mask for moe topk (#3705) 2025-02-21 02:17:23 +08:00
Ke Bao
ddcf9fe3be Optimize triton attention custom mask (#3731) 2025-02-21 00:54:41 +08:00
HAI
6252ade985 revert BLOCK and num_warps on HIP (#3722) 2025-02-20 23:30:18 +08:00
yizhang2077
1eb8eade2b add control for cutlass fp8 blockwise gemm (#3727) 2025-02-20 16:10:35 +08:00
Chayenne
3c7bfd7eab Docs: Fix layout with sub-section (#3710) 2025-02-19 15:44:30 -08:00
simveit
bb121214c2 Variance measure for reasoning benchmark (#3677) 2025-02-20 03:49:49 +08:00
Shi Shuai
55de40f782 [Docs]: Fix Multi-User Port Allocation Conflicts (#3601)
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
Co-authored-by: simveit <simp.veitner@gmail.com>
2025-02-19 11:15:44 -08:00
Cheng Wan
6b0aeb58fd [moe] optim: reduce memory consumption in fused_moe (#3692) 2025-02-20 02:25:05 +08:00
Peter Pan
bb3e526823 [k8s] remove unnecessary hostIPC for security concern (#3700) 2025-02-20 02:11:21 +08:00
Zhanghao Wu
f93e915817 [Docs] Add SkyPilot DeepSeek example (#3706) 2025-02-20 02:10:23 +08:00
Xiaoyu Zhang
55a7ec388f use warp shuffle style reduce and flashinfer vectorize (#3628) 2025-02-19 20:53:51 +08:00
Yineng Zhang
fe0673f1cc set NCCL_IB_GID_INDEX=3 for multi node NVIDIA InfiniBand if needed (#3698) 2025-02-19 20:50:22 +08:00
Mick
99c1b9d2ee fix: apply cache size limit of attention mask for VisionAttention (#3657) 2025-02-19 20:16:48 +08:00
who who who
634a3561ac AMD Prefill optimize (#3665)
Co-authored-by: AMD-dteng <dteng@amd.com>
Co-authored-by: HAI <hixiao@gmail.com>
2025-02-18 09:35:58 -08:00
Mick
424848d26f fix: remove dependency on latest transformers impl (#3635) 2025-02-19 01:14:11 +08:00
Ke Bao
e5ce395a6c Fix draft decode max batch size (#3676) 2025-02-18 23:03:26 +08:00
Yineng Zhang
f983213a1f update pr-test (#3663) 2025-02-18 17:23:43 +08:00
Baizhou Zhang
67fc595bb8 [Feature] Apply Cublas Grouped Gemm kernel (#3629) 2025-02-18 15:18:31 +08:00
Yineng Zhang
07ab4d4a2d fix #3654 2025-02-18 15:16:16 +08:00
saienduri
522e18eaeb Update amd docker image. (#3654) 2025-02-17 20:12:55 -08:00
ybyang
c51dc2cc8d Docs: Deploy multi-node inference (LWS method) using sglang in a K8s cluster (#3624) 2025-02-17 18:14:20 -08:00
yigex
ddf39d3fce [ROCm] Optimal MOE Tuning for AMD Radeon Graphics (#3567) 2025-02-17 17:54:10 -08:00
Wen-Heng (Jack) Chung
2eab113206 [ROCm] Add additional block quant GEMM tuning configs for AMD GPUs. (#3616)
Co-authored-by: HAI <hixiao@gmail.com>
2025-02-17 15:54:18 -08:00
Yineng Zhang
058d199d4e use transformers 4.48.3 (#3650) 2025-02-18 04:40:47 +08:00
Yineng Zhang
a5375adc3a chore: bump v0.4.3.post2 (#3645)
Co-authored-by: pankajroark <pankajroark@users.noreply.github.com>
2025-02-18 02:48:30 +08:00
Yineng Zhang
75d171a9c5 chore: update flashinfer v0.2.1.post2 (#3644) 2025-02-18 02:47:42 +08:00
Yineng Zhang
714f3e6362 feat: support flashinfer mla with prefix cache (#3643) 2025-02-18 02:06:43 +08:00
Xiaoyu Zhang
c38f3aed24 support multi-gpu block-gemm tuning (#3639) 2025-02-18 00:00:35 +08:00
Yineng Zhang
2e6be53e7d fix Dockerfile.rocm 2025-02-17 22:13:03 +08:00
Yineng Zhang
e782eb7e6a chore: bump v0.4.3.post1 (#3638) 2025-02-17 21:58:19 +08:00
Yineng Zhang
e319153be8 update unit test (#3636) 2025-02-17 21:06:10 +08:00
Yineng Zhang
32b44d2fca add mtp unit test (#3634) 2025-02-17 19:04:07 +08:00
Yineng Zhang
5f1a485d9e Revert "[ROCm] Use tl.range() in block GEMM kernels with `num_stage… (#3632) 2025-02-17 18:01:21 +08:00
Shenggui Li
c9565e49e7 [docker] added rdma support (#3619) 2025-02-17 15:36:16 +08:00
Shi Shuai
d03c4c25a7 [docs] Update sampling_params.md (#3617) 2025-02-16 18:52:30 -08:00
simveit
8f13377dea Draft of updated doc for sampling params. (#3260)
Co-authored-by: shuaills <shishuaicareer@gmail.com>
2025-02-16 14:28:22 -08:00
simveit
3d4a8f9bc0 Benchmark for reasoning models (#3532)
Co-authored-by: Chayenne <zhaochen20@outlook.com>
2025-02-17 03:07:30 +08:00
saienduri
7474bed883 Update to latest amd image. (#3597) 2025-02-17 00:29:47 +08:00
Wen-Heng (Jack) Chung
03caefeb51 [ROCm] Use tl.range() in block GEMM kernels with num_stages set by host. (#3535)
Co-authored-by: HAI <hixiao@gmail.com>
2025-02-16 01:40:38 -08:00
Mick
bcc213df61 Model: Support Qwen 2.5 vl (#3258) 2025-02-16 00:58:53 -08:00
Jiada Li
39416e394a fix lockfile and port_registry file permission error (#3598)
Co-authored-by: jiada li <jiada@lmsys.us-northcentral1-a.compute.internal>
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
2025-02-15 19:14:45 -08:00
Shenggui Li
231c40d859 [docs] added favicon to sphinx html (#3564) 2025-02-15 10:21:21 -08:00
Yineng Zhang
bbc47c348f fix apply_token_bitmask_inplace_cuda (#3594) 2025-02-15 23:55:08 +08:00
Yineng Zhang
dfce926921 fix high qps crash when enable mtp (#3592)
Co-authored-by: ispobock <ispobaoke@hotmail.com>
2025-02-15 23:11:28 +08:00
Yineng Zhang
6718b10996 fix eagle unit test (#3591) 2025-02-15 23:10:48 +08:00