Yineng Zhang
|
55842eb81a
|
feat: fused_moe fp8 monkey patch (#2174)
|
2024-11-25 17:06:36 +08:00 |
|
Byron Hsu
|
4b0a1c9365
|
Replace prob based with threshold based load balancing (#2170)
|
2024-11-24 23:17:11 -08:00 |
|
Lianmin Zheng
|
8e1adb8441
|
Allow overwrite flashinfer use_tensorcore (#2169)
|
2024-11-24 20:58:17 -08:00 |
|
Xiaoyu Zhang
|
dd44173dad
|
[Fused moe] add tuning fused configs for qwen2 57b and mixtral 8x7b (#2167)
|
2024-11-25 10:37:50 +08:00 |
|
Lianmin Zheng
|
be0124bda0
|
Rename triton_fused_moe -> fused_moe_triton (#2163)
|
2024-11-24 08:12:35 -08:00 |
|
Lianmin Zheng
|
731146f6cb
|
Fix mixed chunked prefill in overlap mode (#2158)
|
2024-11-24 07:17:37 -08:00 |
|
Yineng Zhang
|
fa27161380
|
fix: use torch.sum for compatible (#2161)
|
2024-11-24 22:37:04 +08:00 |
|
Lianmin Zheng
|
5652c56535
|
Update CI threshold & Improve code style (#2159)
|
2024-11-24 06:29:38 -08:00 |
|
Yineng Zhang
|
e3938b2f9c
|
feat: update other MoE models deps (#2156)
|
2024-11-24 21:36:34 +08:00 |
|
Lianmin Zheng
|
c211e7b669
|
Simplify batch update (#2154)
|
2024-11-24 04:47:10 -08:00 |
|
Yineng Zhang
|
d90c3d6b8b
|
fix: resolve end-of-file-fixer (#2157)
|
2024-11-24 20:38:26 +08:00 |
|
Yineng Zhang
|
9e8f8fbf95
|
feat: update gitignore and add tuning config for FusedMoE (#2155)
|
2024-11-24 20:24:58 +08:00 |
|
Yineng Zhang
|
b509db5832
|
feat: remove the dependency on FusedMoE (#2153)
|
2024-11-24 20:09:27 +08:00 |
|
Henry Hyeonmok Ko
|
dbe1729395
|
Merged three native APIs into one: get_server_info (#2152)
|
2024-11-24 01:37:58 -08:00 |
|
Byron Hsu
|
52f58fc42a
|
fix dp_rank env (#2144)
|
2024-11-23 11:46:21 -08:00 |
|
Byron Hsu
|
cbedd1db1d
|
[router] cache-aware load-balancing router v1 (#2114)
|
2024-11-23 08:34:48 -08:00 |
|
Yineng Zhang
|
ad47749b82
|
fix: resolve bench_serving args (#2139)
|
2024-11-23 17:45:42 +08:00 |
|
Lianmin Zheng
|
751c3a037c
|
Fix dp print message (#2138)
|
2024-11-23 01:22:26 -08:00 |
|
Yunmeng
|
60769be14d
|
Add concurrency option for benchmark (#2136)
|
2024-11-23 17:07:07 +08:00 |
|
Lianmin Zheng
|
a78d8f8db3
|
[CI] Fix test cases (#2137)
|
2024-11-23 01:00:07 -08:00 |
|
Ke Bao
|
c5f865013e
|
Fix grid size in Triton decoding kernel (#2134)
|
2024-11-23 16:51:46 +08:00 |
|
Jani Monoses
|
d98fa1e93d
|
Add simple CPU offloading support. (#2081)
|
2024-11-23 06:23:53 +00:00 |
|
Ankur Neog
|
865233e256
|
Add initial support for intel Gaudi accelerators (#2121)
|
2024-11-22 20:22:23 -08:00 |
|
Lianmin Zheng
|
66d4859acf
|
Revert "Only stream output on tp rank 0" (#2130)
|
2024-11-22 15:46:16 -08:00 |
|
Lianmin Zheng
|
e1b63624d7
|
Only stream output on tp rank 0 (#2124)
|
2024-11-22 15:13:44 -08:00 |
|
Henry Hyeonmok Ko
|
c35cd1f8c7
|
Expose max total num tokens from Runtime & Engine API (#2092)
|
2024-11-22 15:10:10 -08:00 |
|
Xuehai Pan
|
62a4a339eb
|
docs: fix module docstrings and copyright headers (#2077)
|
2024-11-22 22:16:53 +08:00 |
|
Yineng Zhang
|
2797bc3422
|
fix: add xgrammar dependency (#2126)
|
2024-11-22 20:53:11 +08:00 |
|
Yineng Zhang
|
9a00e6f453
|
chore: bump v0.3.6 (#2120)
|
2024-11-22 19:27:30 +08:00 |
|
Yineng Zhang
|
4f8c3aeafc
|
minor: update gsm8k threshold (#2125)
|
2024-11-22 19:23:58 +08:00 |
|
Lianmin Zheng
|
2369e88209
|
[minor] Clean up unused imports (#2122)
Co-authored-by: rinrin32 <rinrin.int@gmail.com>
|
2024-11-22 01:50:42 -08:00 |
|
bjmsong
|
ad30d5cf9a
|
Benchmark with Pytorch Profiler easily (#2110)
Co-authored-by: root <bjmsong@126.com>
|
2024-11-21 23:29:50 -08:00 |
|
Lianmin Zheng
|
dfec7fca06
|
Rename sglang.bench_latency to sglang.bench_one_batch (#2118)
|
2024-11-21 20:07:48 -08:00 |
|
Jake Poznanski
|
8048c28c11
|
Fix #2037 - Context length check does not take into out pad tokens for visual models (#2106)
|
2024-11-21 19:05:41 -08:00 |
|
Byron Hsu
|
30af7dfb34
|
[router] add base_gpu_id server args & merged radix tree python reference (#2115)
|
2024-11-21 17:13:33 -08:00 |
|
James Xu
|
f6f713797b
|
Add support for Qwen2-VL-based embedding models (#2055)
|
2024-11-21 14:24:25 -08:00 |
|
HAI
|
f35cb46cc3
|
ROCm: Fix MoE padding for none FP8 cases (#2111)
|
2024-11-21 12:23:21 -08:00 |
|
Jerry Zhang
|
7f8fcd39cd
|
Turn off autotune for scaled mm for fp8 dynamic quant in torchao (#2116)
|
2024-11-21 12:19:49 -08:00 |
|
Jerry Zhang
|
5c6a41facf
|
Error out when torchao-config option is not recognized (#2107)
|
2024-11-20 17:37:28 -08:00 |
|
Lianmin Zheng
|
722530fa01
|
Enable overlap scheduler by default for the triton attention backend (#2105)
|
2024-11-20 02:58:35 -08:00 |
|
Lianmin Zheng
|
3295cd8af2
|
Allow skipping warmup in bench_offline_throughput.py (#2103)
|
2024-11-20 01:25:21 -08:00 |
|
Ying Sheng
|
5942dfc00a
|
[feat] Add session control (#2073)
|
2024-11-20 00:36:53 -08:00 |
|
Lianmin Zheng
|
7d671e4ad2
|
Enable overlap by default (#2067)
|
2024-11-19 22:07:58 -08:00 |
|
Ke Bao
|
699384cb01
|
Set schedule policy more conservative for DP attention (#2096)
|
2024-11-19 20:57:18 -08:00 |
|
Lianmin Zheng
|
ffd20fcd03
|
Make constrained decoding work for overlap scheduler (#2095)
|
2024-11-19 15:04:43 -08:00 |
|
Yineng Zhang
|
55bd97f3e5
|
minor: add dataset dump and questions shuffle (#2093)
|
2024-11-19 14:07:27 -08:00 |
|
HAI
|
e57c3e12b8
|
Use native fp8 format on MI300X (#2094)
|
2024-11-19 14:06:29 -08:00 |
|
Alexander Waitz
|
929c7621af
|
Fix: incorrect top_logprobs in chat completion (#2088)
|
2024-11-19 12:21:36 +00:00 |
|
Lianmin Zheng
|
b7a065eae3
|
Use cuda event wait and synchronization instead of busy waiting (#2089)
|
2024-11-19 00:21:46 -08:00 |
|
Lianmin Zheng
|
b110453802
|
Simplify logits penalizer (#2086)
|
2024-11-18 17:48:28 -08:00 |
|