55 Commits

Author SHA1 Message Date
a7a2c722af fix large completion probe timeout 2026-07-15 22:20:25 +08:00
163da44dfd record current performance experiments 2026-07-15 21:11:32 +08:00
9fc7e98af4 fastpath oversized basic test outputs 2026-07-15 17:18:39 +08:00
2b7880efa7 fix platform basic test compatibility 2026-07-15 14:25:52 +08:00
e374b14bf9 add moe bucket profiling and record bottlenecks 2026-07-15 11:34:59 +08:00
8b4ee2ff8b record max batched tokens 8192 experiment 2026-07-15 10:44:24 +08:00
2c7a8d12b3 record max batched tokens 32768 experiment 2026-07-15 10:27:33 +08:00
59e497fdc9 disable profiling trace by default 2026-07-15 04:43:46 +08:00
cb962589e9 revert moe router topk softmax experiment 2026-07-15 04:21:03 +08:00
eea0653ace experiment moe router topk softmax 2026-07-15 04:19:56 +08:00
16d52b469c record 245k platform-equivalent benchmark 2026-07-15 03:55:20 +08:00
3cf62afaaa stabilize platform launch and record official-like baseline 2026-07-15 03:23:39 +08:00
f49b8a51ec document docker build line ending fix 2026-07-15 01:54:56 +08:00
f3303b3b26 enforce lf line endings for docker build scripts 2026-07-15 01:40:40 +08:00
4b89576cbf reduce docker build context and match working baseline 2026-07-15 01:32:21 +08:00
d1f8048b6e record moe tiny batch matrix results 2026-07-15 01:28:06 +08:00
af375830c7 align platform build config with working submission 2026-07-15 00:49:24 +08:00
62f10c3375 restore official docker build baseline 2026-07-14 23:03:24 +08:00
3a06e4f0e5 restore standard Dockerfile submission name 2026-07-14 22:37:08 +08:00
3ec5e7911f normalize DockerFile formatting 2026-07-14 22:19:00 +08:00
ae64b20e22 match official DockerFile submission name 2026-07-14 22:17:12 +08:00
2c6cabcc63 optimize moe tiny batch tokenwise path 2026-07-14 21:49:55 +08:00
0597fa6c6d profile decode path and optimize tiny batch moe 2026-07-14 20:44:05 +08:00
a5abd66e21 test eager and custom allreduce toggles 2026-07-14 19:18:46 +08:00
82c1463b0c document multi-step scheduler diagnostics 2026-07-14 18:17:42 +08:00
465a9c8995 add decode throughput analysis 2026-07-14 17:11:28 +08:00
b41e7cd899 log seq2 benchmark experiments 2026-07-14 15:27:52 +08:00
61e169fe18 add cumulative prefix benchmark generator 2026-07-14 14:21:23 +08:00
c8cc9401a4 baseline working model service and perf tooling 2026-07-14 13:57:40 +08:00
1902c81fdd fix issue of loading weight 2026-06-30 09:55:13 +08:00
f89bc60d59 fix multiple issues 2026-06-26 17:23:55 +08:00
810874ddb8 enable prefix caching 2026-06-26 13:27:52 +08:00
c84151eef9 fix issues 2026-06-26 12:55:02 +08:00
liwei02
3d62430fd7 调整配置参数 2026-06-25 17:36:43 +08:00
72aa7e690a Add README and start commands 2026-06-23 17:17:22 +08:00
b5806731e0 some op overhead optimization 2026-06-19 11:19:39 +08:00
47a4d9e72a fix no reasoning token issue 2026-06-18 12:21:05 +08:00
3b8a567e9e fix serving issues when requesting real data 2026-06-12 17:57:23 +08:00
50e3a05fb0 fix incorrect MoE step to ensure decoding speed 2026-06-12 11:44:50 +08:00
629f878c28 initial commit for qwen3.6-moe adaptation 2026-06-12 10:10:49 +08:00
365da18436 Add reasoning parser mechanism + qwen3 parser + bugfixes 2026-06-10 18:22:29 +08:00
4ab36b51d5 Add qwen3_coder tool calling parser 2026-06-10 14:38:54 +08:00
d972854fb7 fix completion token statistic bug when input context is large 2026-06-08 15:04:34 +08:00
c2de1c83b0 Utilize chunked prefill + K-tiling techniques to ensure 100K context 2026-06-05 17:00:41 +08:00
2d1ef50992 chunked prefill support and memory opts 2026-06-05 16:03:34 +08:00
8c047a70ea some modifications to ensure 50K context input 2026-06-04 17:56:29 +08:00
1c33ef1355 add paged_attn 2026-05-29 16:53:39 +08:00
3ef8227384 initial version of adding chunked attention, ensuring 20K context 2026-05-29 16:49:33 +08:00
0e89906481 Qwen3.6-27B iluvatar bi-v100 adaptation 2026-05-21 16:37:24 +08:00
fad74b701b Update to new version of base image 2025-10-24 15:45:06 +08:00