qqtang/sskj - sskj - 是石科技代码管理系统

qqtang/sskj

Fork 0

Commit Graph

Author	SHA1	Message	Date
yy-fighting	3b0297516e	fix: replace 5 buggy parse_results.py (raw_requests bloat) with shared parse_backend.py wrapper	2026-07-22 03:47:22 +00:00
yy-fighting	31a21631b8	fix(parse_results): 不再把 raw_requests 嵌入 results.json，避免 8.5MB 膨胀 parse_jsonl 当 raw 文件是单个聚合 JSON 对象时返回 [data](整个聚合含 itls/generated_texts 数组)，原代码把它当 raw_requests[:100] 塞进 scenario，导致单次 bench 的 results.json 膨胀到 12.5MB(itls 6.95MB + generated_texts 1.54MB)。而真正有用的聚合百分位已在 latencies 字段(~0.5KB)，逐请求原始数据已在 raw_outputs/*.jsonl，raw_requests 字段纯冗余。 - 移除 scenario dict 的 raw_requests 字段; parse_jsonl 返回值改用 _ 接收 - 符合 BENCHMARK_WORKFLOW.md: 产生大量请求时逐请求数据存 raw_outputs, results.json 只留聚合百分位 - 实测 qwen3_235b results.json: 12.52MB -> ~KB - 同步修改 4 份相同 md5 的 parse_results.py(本提交含 3 份 tracked; qwen3_8b 未跟踪待随实验提交) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-21 10:05:31 +00:00
yy-fighting	3f28edd1a6	feat(p800): add Qwen3-235B-A22B SGLang TP=8 benchmark experiment Deploy Qwen3-235B-A22B on 8x Kunlun P800 XPU (TP=8) via sglang, adapted from the proven qwen3-8b launch (attention-backend kunlun, dtype float16, mem-fraction-static 0.9, XSGL_* XPU env vars). TP bumped to 8 with all 8 /dev/xpu* devices; context-length 8192 (the 8b used 4096 which truncated 2 outputs at 2k+2k). Patch qwen3_moe.py in the sglang image: load_weights assigned to the read-only @property routed_experts_weights_of_layer, raising AttributeError for any qwen3 MoE model (Qwen3-8B is dense, so unaffected). Fix: assign to the private _routed_experts_weights_of_layer, applied idempotently in start_server.sh on every start. bench_serving: isl=2048 osl=2048 concurrency=16 num_prompts=160. 160/160 success in 771s. Summary in results/qwen3_235b_tp8_run1/report.md. Server on port 30010 (30000 held by the lingering qwen3_8b_bench_tp1). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-21 06:34:57 +00:00

Author

SHA1

Message

Date

yy-fighting

3b0297516e

fix: replace 5 buggy parse_results.py (raw_requests bloat) with shared parse_backend.py wrapper

2026-07-22 03:47:22 +00:00

yy-fighting

31a21631b8

fix(parse_results): 不再把 raw_requests 嵌入 results.json，避免 8.5MB 膨胀

parse_jsonl 当 raw 文件是单个聚合 JSON 对象时返回 [data](整个聚合含
itls/generated_texts 数组)，原代码把它当 raw_requests[:100] 塞进 scenario，
导致单次 bench 的 results.json 膨胀到 12.5MB(itls 6.95MB + generated_texts 1.54MB)。
而真正有用的聚合百分位已在 latencies 字段(~0.5KB)，逐请求原始数据已在
raw_outputs/*.jsonl，raw_requests 字段纯冗余。

- 移除 scenario dict 的 raw_requests 字段; parse_jsonl 返回值改用 _ 接收
- 符合 BENCHMARK_WORKFLOW.md: 产生大量请求时逐请求数据存 raw_outputs, results.json 只留聚合百分位
- 实测 qwen3_235b results.json: 12.52MB -> ~KB
- 同步修改 4 份相同 md5 的 parse_results.py(本提交含 3 份 tracked; qwen3_8b 未跟踪待随实验提交)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-07-21 10:05:31 +00:00

yy-fighting

3f28edd1a6

feat(p800): add Qwen3-235B-A22B SGLang TP=8 benchmark experiment

Deploy Qwen3-235B-A22B on 8x Kunlun P800 XPU (TP=8) via sglang, adapted
from the proven qwen3-8b launch (attention-backend kunlun, dtype float16,
mem-fraction-static 0.9, XSGL_* XPU env vars). TP bumped to 8 with all 8
/dev/xpu* devices; context-length 8192 (the 8b used 4096 which truncated
2 outputs at 2k+2k).

Patch qwen3_moe.py in the sglang image: load_weights assigned to the
read-only @property routed_experts_weights_of_layer, raising
AttributeError for any qwen3 MoE model (Qwen3-8B is dense, so unaffected).
Fix: assign to the private _routed_experts_weights_of_layer, applied
idempotently in start_server.sh on every start.

bench_serving: isl=2048 osl=2048 concurrency=16 num_prompts=160.
160/160 success in 771s. Summary in results/qwen3_235b_tp8_run1/report.md.
Server on port 30010 (30000 held by the lingering qwen3_8b_bench_tp1).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-07-21 06:34:57 +00:00

3 Commits