gitcommit90's picture
Publish runtime v2 optimization, final comparisons and figures (weights unchanged)
8edc128 verified
Raw History Blame Contribute Delete
23.6 kB
8951a99119cdcd06c699d91ccc5db0a40b595961041a5ec2e6103b88112757e8 .gitattributes
c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4 LICENSE
f7e05b28104f305f9fe6bf5cd25bc17e67c72cd8a7b0b29ea511f5f7f3a966bc README.md
a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715 chat_template.jinja
5bec5643138a09f2917a0b7471a673baecfbf85f59af49cc048f4318f32e7a3d config.json
ccdb9203010fc0534d37b0b475d85f088f5e62568d3cbd76229af4d8e50ffb28 evaluation/QUALITY_GATES.md
021b420e4757b37909200d1cc52bf308116461735a6b50c67df652267f54c587 evaluation/compare_vs_ref.json
5d01579bee6c0863addc3236392b4d88c8d7a7d3cf66b62ae65db1430c0110a3 evaluation/eval_data_MANIFEST.json
6df2bf0438b64d1353c1737e3659c86bce501dc188de9ce448492895e8b5ae63 evaluation/harness/build_eval_data.py
e2818e8c8ff581d65ac8a4dbfc07b58eaea97546dfd63cc3f8f31faaf8ed0f22 evaluation/harness/common.py
0423139c0573e09181f065dbdb273b123aa4a966a5ec57a3643b2fe4f8f43b92 evaluation/harness/compare.py
535255ccff9b6032494d918331dce7d7bbd5a455771143afeaf7977458b52bf4 evaluation/harness/ifeval_lite.py
c0e6d611823b672513730fae4f83d6e72cb0927202a0df1112176465d316731f evaluation/harness/mock_server.py
8909f46e7c6383cce45dbad9c64d78035316031b6f7d99be664ae8b7c3d3577a evaluation/harness/perf_bench.py
d2b24fe51830bf6ed99af01c66ed1b861a50eff88d130fac3f9369e6865837cd evaluation/harness/requirements.lock
49f85f32fb01f029182491d5dd803c26c37814e9ecfa283f37d705543242bc3d evaluation/harness/run_eval.py
fe25e6a9d5432922ff4509a9a80e7b996072ee2091353840a6d0fdf764d8daef evaluation/harness/tasks.py
8c28fad23d10bfa56897a6c0d306b0a474cb6bc2ac7a08355682bd697a2dcd3f evaluation/harness/test_harness.py
ec6899745f66eaf5eb92975341bd44b8c6d5ede2116ea6d0d56d8ba008ae7702 evaluation/harness/tool_cases.py
90dbf7789104b8763f8980f564d8da2c6d033a2207707a386dba8756cd8d2063 evaluation/hf_bf16_checks.json
a1a5de6483f0d8c2d759b9c60cb86da4794a4036c6101bba104cc1d5dba63dfb evaluation/kernel_summary.txt
ce49434ad0c1806bcf01a57957add6fb2ca67f1aa6a61394ae248a75d41b7c80 evaluation/nvfp4_v1_mtp_release_probe.json
4cfff7659e057c02133576124dd0dd65b28a8d6869d1b460d68055dc01a2454a evaluation/nvfp4_v1_probe.json
a588317f6ba1071ab5f67a850e0ced977dfbf3f3dd0b34ea2d5ac54767947c17 evaluation/perf_sglang_bf16.json
7f9aa0a53f019234a256057b0f759695cf0ac266ac033e3e02b84bf71ffcec41 evaluation/perf_sglang_bf16_mtp.json
8a115863344c244470a3a18959e89c914aa852602e75cb365554d62adfd66c9f evaluation/perf_sglang_nvfp4_v1.json
d68a9f7a151718b65b6782ea48f4db0aa60f068ab8636eb51f2f2935a61b0058 evaluation/perf_sglang_nvfp4_v1_marlin_w4a16.json
546730231cdf739cf84f0d92768c2a31378c165b3e48a1840117b9a2faa5035a evaluation/perf_sglang_nvfp4_v1_mtp.json
8f50277ef8a232dc4abab998fa80ffdcc46c13cbebea1d9328e93878af035157 evaluation/sglang_bf16_mtp_probe.json
92c0708bb0d27772bedefc3d5f458b742c48325025af5a1269535de6dca2d914 evaluation/sglang_bf16_probe.json
ec88f909edcbf225936bbeac88ede9312520593eb53db976d5079d9dd6c45ed1 evaluation/summary_sglang_bf16.json
58cd6bbadfc9fc070a784e65810414a24919084e4570e1ff7680e8a00f14504b evaluation/summary_sglang_bf16_mtp.json
c6d75330180b2d1bd5f2dda574afeee8844e18e44c46ba0f3a1128eb052d2326 evaluation/summary_sglang_nvfp4_v1.json
aff7bcc52ad3e83e6394a8d31e733d8b5725d213836beb98824c397e726c66c6 evaluation/summary_sglang_nvfp4_v1_marlin_w4a16_gsm8k.json
944d3ce06cffbfb7a8e10c1af186aaa62a196e6b96cd8c3a1e6800e5d998fa70 evaluation/summary_sglang_nvfp4_v1_mtp.json
cc0be931111ecb00e1ceef1d24adfa6cd1e0af04167ce6d3a999a0cc08883d89 figures/README.md
47eecb7dab94c2cbe44756977f2e4e81380a059f1661060c0ac5e0909d9b1c24 figures/performance-summary.pdf
7012b65a258263617bcd3a9d57e93c4cb24836d9da35a69d723a0f6ef6416d68 figures/performance-summary.png
975894bd93a506565d81573ecfc75b9e6202406c2f21940750ec1ad7c9635e8c figures/performance-summary.svg
058f67de2a71ee67cf48f4976b69d353cfaea0607bb2d91a20e33774c35c2df7 figures/plot_benchmarks.py
277d66c8e57b9fe00c599a526d378e798d55be661d1a29da9ee6fb4eaaa691e0 figures/plot_runtime_v2.py
ceca3cd14f612774aad2f9f076a1d77177bd6f6090c41f8a3ca985318ada3793 figures/quality-summary.pdf
761cb0de5f120ec2934b7b900b0d4961464ba24686b4175095289e9d245b0a04 figures/quality-summary.png
0315f8e622b4b9cb9ca36ed3718403ba64ea4f8f3df582853fd3e4c0b4fe15c5 figures/quality-summary.svg
472fcc1fa6325424ea016e5fb386728d1bf661e21582f7e2e829387053eb9a0e figures/requirements.txt
a2e2fe69b92b12eaedab329f96b8434fb5f42cbfdbefb7a16742be9dd62e0906 figures/runtime-v2-performance.pdf
6b0145854cf885771b77dd327e3d5cb0a742b04c9c744bf24006ba98f4569313 figures/runtime-v2-performance.png
4de7bc0cd7d6f953bf1c864b0a66dbda1ef425d18c5f98d2ca14396df8e61f98 figures/runtime-v2-performance.svg
8c26bbb48e9646822b64e2624b94cb4b4502c2d0987e74b6eff0b2cec17f4a09 figures/runtime-v2-quality.pdf
c66a6044c2160795ef18de6906060864ed793adfe08a27a8fce20e5f59306695 figures/runtime-v2-quality.png
d6422b140d441f9028b53b6f6035cb3296a4c55f96b1ecbfc249e0644136e6ab figures/runtime-v2-quality.svg
f288bb4281580138395c6acc7b3adb62f45c21530bc0708cb2cf9edf093f6a4f generation_config.json
b197af747a1f072419a8e7e2db3252d9aeea84d21f65db37f748430ab7f83bfd hf_quant_config.json
1e420ea69111b7bb3c7c529cdbbb4ff4e6ebb531c0cd2be5c634cd88cd40eaca model.safetensors
26e11d3522aa730c0ba031340ce42632bc2834da8cc0b6804006bb207d979a5b modeling_sensenova_loop.py
3a159dfec9978a186a72ba085e0ad6a050f3968d8b364218d7bd13f5c89381f2 preprocessor_config.json
d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1 processor_config.json
df49d802cffe959b3176eed9abee2277d3e4291cdaf2d9abf8430ee17aeba700 quantization/10_reference_checks.py
67d6edacb11e519afb6d81adb4c559930b17ce9a8adeed0e7c8c2043d8383337 quantization/20_quantize.py
27dcbf33dfb7e83cace92cc8221e20d2ead29d4090bf15c9348e181b6bb5ba47 quantization/30_verify_export.py
dc54da6f2e37136c3172779d86ae0134a353942f341eaa8934d3000a01f34682 quantization/build_calib.py
04c164fb57e8125eed5d624cefa806a61bc28cb929aca6406d2923ea43f11825 quantization/calib_v1.jsonl.sha256
3a2015bbf02262d97e0de28f4fa2b3e73d43f58635a507a96788bf7b587236d8 quantization/calib_v1.meta.json
4d71bc0045ee80c45f5eef89e5e721e064e2505020b327942501b017daf0fdf8 quantization/quantization_stats.json
723419a376e5f2339f4f0d4f9376b16ea2d5359e54659ccb85c2bb2d5c3028fd quantization/requirements-quant.lock
be632c83213d44b4a18f367c59fcb55f5d0d738b8c67f64ccc61df3c6a9fb598 quantization/verify.json
32dae3052f331ee34d628ef535709b301259a45df7c7522c4d35dcf49873f00b runtime-v2/.gitignore
4aa348318e825643f1edb8b4516862de1dca0cc6c56960b10619676a03b6a5ac runtime-v2/LEDGER.md
f43e21163bea7f9f6e9adcd73c8ac9914fc4b4988f0ef917b2071792c94879f4 runtime-v2/README.md
5373b331a9ad0ca78e3bf362f4d3974808e8f820366781c76318f8abfa23c9d0 runtime-v2/RESULTS.md
8d58f6918095d93a67b83b267ee51e48e5895b2d54e30ccdd5d2b7c7e60128ac runtime-v2/bench/README.md
4b5700057f8bbabf7a42e40fcf361710fb0a1976a9353abbdc1d79bc38ef564e runtime-v2/bench/fp4_gemm_bench.py
95a4ed870e9bb68e143fa459a55eb84963617ba5f0cda023a35f6e08082a17f3 runtime-v2/bench/prof_drive.py
b95119c8ad457bf182319d4a8e10cc67d278efa9c5458a0caa2df4d941372e44 runtime-v2/bench/report_tables.py
27e569ec5be6157c31e81ff6d09c62871542e82b1a397c95961a8a347e60de65 runtime-v2/bench/screen.py
d548ad5c9741c59e51e32a78a39c305594a62a12bf13b06b06195b6f5d1f5c2f runtime-v2/bench/trace_graphs.py
8117abdb9b399c44a57ee0a5ad32831df0d83fc68880e60e24cb9ca65fee74fa runtime-v2/bench/trace_summary.py
5bb587d19dce89cbce317a812a17e30891150afca578f60aa94f1a77b4070c46 runtime-v2/bench/trace_summary_lib.py
2f1d8b4d676321dce894f03f97fa17d99842a73054605d9e7f70c3f8426bc806 runtime-v2/bench/wait_ready.sh
e00d2fafe780fcf4c04ab52b040e43ec7143c7bd6e070637563f2724b59888d1 runtime-v2/overlay/python/sglang/srt/configs/__init__.py
bdc7fa2055b799ce07441a5d499fafa554b7b797d4c4a24fd251b846b51260fd runtime-v2/overlay/python/sglang/srt/configs/model_config.py
eb6df8f37ac06e6f439dd24f687e5bf1078599ade28acaa20d8799bf77c7e057 runtime-v2/overlay/python/sglang/srt/configs/sensenova_loop.py
b3b4959f2336d1afdf4f0353a0a0eecfc38495226912022dd862489cbb532c98 runtime-v2/overlay/python/sglang/srt/layers/rotary_embedding/mrope_rope_index.py
68bc3cfe9749f90ecc817ccede7fdbd9167684e902637dbec0b738a9d7ea7e25 runtime-v2/overlay/python/sglang/srt/layers/sensenova_mhc_fused.py
87ccee5659fb8d95f7f54a038d7d0f71ba8afab04684c72c6bd1556e31d119ce runtime-v2/overlay/python/sglang/srt/models/sensenova_loop.py
7fc07bd18b974aa8f54013f2bb39536a65d32ad0cc1a1df2d239ead0dc136754 runtime-v2/overlay/python/sglang/srt/multimodal/processors/qwen_vl.py
68e1076237ed67adfa06530139d79df0783a2519620443a58cce94c5143d56c4 runtime-v2/overlay/python/sglang/srt/utils/hf_transformers/common.py
d93e6342f9487567a7847443eb47b41701b4510474cd5664c8dc51b37eb6f6fd runtime-v2/patches/model_config_mtp_draft.patch
029fa25bb4ea5a16c9fce8de412e7ea6481fc540508c63bdd629026b9a56f926 runtime-v2/patches/sensenova_loop_quant.patch
cfd86c1b46c3ac7592ed50ec5641d36e1a69025791bd986907b3c6b54c31a4b6 runtime-v2/patches/v2_mhc_fused_router.patch
aeabae0b23eb5eea12d4d5c9fc57b115bbf702d90019a61cb1bdd6b912cde07e runtime-v2/runs/chain1.log
8eac091fab019b0d871b8c20c4ef240f758ef512fefa7bdb2e5f3dd6267df276 runtime-v2/runs/chain2.log
76984e7fc55c0065fb8c9d1646b4f61de0c24b9700fd21348fce82f1fffa5a22 runtime-v2/runs/chain3.log
f82fb0102b5a9cea9aa39c720d35781128a7d4330d26e808a101ecbaef4c617a runtime-v2/runs/final_chain.log
3cb5e44353508026e19a34c728a0cfd62b234a1de02bb2e501bd904b856be246 runtime-v2/runs/final_frozen_v1/eval.log
ae09e6590b834fe3d2eb4d0efbe1710f745fb3a2dfb894111035a81c1a0273bf runtime-v2/runs/final_frozen_v1/eval/compare_vs_ref.json
c7b22c9374b33ddbf580521917bb226e1535a28464d682690d4c0b4b74d0af65 runtime-v2/runs/final_frozen_v1/eval/raw_gsm8k.jsonl
6c24a6a63e53f694029de6fd48bf4b0a31e8b3a8d4978ff0c1c2b1274627402f runtime-v2/runs/final_frozen_v1/eval/raw_humaneval.jsonl
d6102c5faacfc6d6460a076c4a4e73c09f4c3fc4b1f69c26694fa473c63a200c runtime-v2/runs/final_frozen_v1/eval/raw_ifeval.jsonl
723bc26360e96ea005eaf282c6c400104ad26a3df22a13328fbdc35b07164549 runtime-v2/runs/final_frozen_v1/eval/raw_mmlu_pro.jsonl
37b7b5b550d8f3ced41d5fc0c33b3268b8112442412bc7e9216d58ccb0c2797f runtime-v2/runs/final_frozen_v1/eval/raw_tools.jsonl
fe1c19237fa5ab99b626d44830afb7dc7c8bc1ecacb1d5b6ac09729f3e6be0cd runtime-v2/runs/final_frozen_v1/eval/raw_vqa.jsonl
233917924301edfed636e906a80fbc7180b0c8f1465fd1df32b2acd6db9159e3 runtime-v2/runs/final_frozen_v1/eval/summary.json
138edee8b67c2f8cdc9fbe34b48067ec99dc9b2b20729611e6a856af6f74af71 runtime-v2/runs/final_frozen_v1/eval_compare.txt
69bf0e6859cd641d10341d0575012918944b49c59b9dada302324cb6b6df1476 runtime-v2/runs/final_frozen_v1/gpu_after.txt
03ff9c79c916f05ec992381c0f635426e32cbe907d41f91d506d4cb1ffdf666c runtime-v2/runs/final_frozen_v1/gpu_before.txt
a3e9d1074d6b2b2d6af2eff5f1c35761e46067243a45c9d318562273dfea5417 runtime-v2/runs/final_frozen_v1/greedy.json
5a29fa8c0bafdc6dcb66c6172008d892cb8144ec5066a2e79d3512b870164c37 runtime-v2/runs/final_frozen_v1/greedy_diff.txt
3d3193ebc85d9703ceca209b0e9b2b8bdf8729dfd40bfb4ca36e1d6b05738ee6 runtime-v2/runs/final_frozen_v1/mem.txt
d835c86c49b359ee814f608bc268ad1c843426bd4722d9b048ac3a7f7ec45579 runtime-v2/runs/final_frozen_v1/perf_matched.json
e292a5bcb39f3793fbf94d7ca6bcaf80f7bd3427e8522fc9ef463646563dbacb runtime-v2/runs/final_frozen_v1/perf_matched.log
c9501741babdc2cbfc877be168b64621cfa1cc65bc4606ed93079b7d9bdbe71c runtime-v2/runs/final_frozen_v1/screen_code.json
6f6459cd295bbe224275e829e2379017f8e7a028a3f03e6de3b67b5ee14ac00d runtime-v2/runs/final_frozen_v1/screen_doc.json
4e2ead04c10b476e955991de1d1527dac816545fea5bac42042cdb12d0453ff4 runtime-v2/runs/final_frozen_v1/startup.txt
1ab6b379ed646e189a284b44408989a79637a2c6f478aa7c03e47dc6b1418f8f runtime-v2/runs/final_v2_exact/eval.log
1be03124a62cea4fe99ea8dae682947570adf8e004061bec0a603bd04935ac42 runtime-v2/runs/final_v2_exact/eval/compare_vs_ref.json
7193b8d845182d28f4f3f71cad94e3db146c65315384ac85b29e39c094e00ce7 runtime-v2/runs/final_v2_exact/eval/raw_gsm8k.jsonl
0017ed83f0e36cd6ec678eb1158efae0bbf850715be242e11ba41fa2fc6a3b5d runtime-v2/runs/final_v2_exact/eval/raw_humaneval.jsonl
b2b5ea9fed29ff5317ee06aa4dee888cb2c60a64d33f188f49b0126797643ed5 runtime-v2/runs/final_v2_exact/eval/raw_ifeval.jsonl
107687c7b517761160a2d8b35ccad29a10ac5667bdbbb3aff60fd20aeda19a92 runtime-v2/runs/final_v2_exact/eval/raw_mmlu_pro.jsonl
975732afa2c61c16dc6e8877c72414adb4f97b2aa778c184ac32f9e33e56b2c1 runtime-v2/runs/final_v2_exact/eval/raw_tools.jsonl
84a9e2908ce2dacc1b863e189ef1223f60f25256f46d3dc8ea0a20886c63106a runtime-v2/runs/final_v2_exact/eval/raw_vqa.jsonl
a50e1b698802fcdc0a1bac9e68a2e73a5fd57c53cdbe1e7bf4767cd776e284fe runtime-v2/runs/final_v2_exact/eval/summary.json
c0e7cb0b03610f45de18bd1ff73e7f9f5c766b1d687229857c69230f3e9e6596 runtime-v2/runs/final_v2_exact/eval_compare.txt
ac7f0ee9c9c9d76b3f78530de8078f14f12b180bfb4bb87a8cb906101e5fc4de runtime-v2/runs/final_v2_exact/gpu_after.txt
33d8f8e097ac88d774be66b5375867309baf2cc1e71b7ddfa083499e04669270 runtime-v2/runs/final_v2_exact/gpu_before.txt
5587c74db231fdb0f009e1fc521673c9464c8d16aa60df08d5729544315786fa runtime-v2/runs/final_v2_exact/greedy.json
5c6c788f0353dd10fb95bbd2cac62af3a774514b3d94acc6f0177f06e17f13cf runtime-v2/runs/final_v2_exact/greedy_diff.txt
4fb42769c273405b3cca964c55857838ec5ae5f505be5aa6608f9873d40abc1a runtime-v2/runs/final_v2_exact/mem.txt
0765ac69ab713c826222911c7a3b348ce6d63622b0990a3d858d6792bb01803a runtime-v2/runs/final_v2_exact/perf_matched.json
8d920e9d0edeeb83fc6f0500dff75a12225bc6d76c3ce59d4d4ceb593cb390b7 runtime-v2/runs/final_v2_exact/perf_matched.log
83ec9f38a72972d41fcd91d40dd7feb13c2dd7a3925f92653b03b93ab750e0c2 runtime-v2/runs/final_v2_exact/screen_code.json
c4e0990219587fe88a78488d08e32fe76eeb4d4d77535626f644e97387595128 runtime-v2/runs/final_v2_exact/screen_doc.json
8ff918ad3e2c406fdc71be2997f998bbe8b71dd9330df1fbe8df4571f590e117 runtime-v2/runs/final_v2_exact/startup.txt
92cbd830f90bd66caa59be28ec3c8a0494abc089100472392eca1636281e292b runtime-v2/runs/final_v2_fast/eval.log
dece7c45c38bcbdb721fabb340b72bc1410735df883146a440aff629bea1998d runtime-v2/runs/final_v2_fast/eval/compare_vs_ref.json
6b8f184b2b8a1af194a06edeaec8a46c5ec1c1deec246f5cf646fe7dcdef3d67 runtime-v2/runs/final_v2_fast/eval/raw_gsm8k.jsonl
40dcf3d22f9c3727e2c6112561cbe128e72180a909ad8e51d8bb8e75d5cba75b runtime-v2/runs/final_v2_fast/eval/raw_humaneval.jsonl
e383f09c1a104b9f0413240e11456b962d9b736ea91fff64eec3daff762b9616 runtime-v2/runs/final_v2_fast/eval/raw_ifeval.jsonl
ccfc6392d774720393c16ce659dfb50b58c110f4e5ea4cb745b3df1ee7bdb4f3 runtime-v2/runs/final_v2_fast/eval/raw_mmlu_pro.jsonl
73d5fc4a7f459500e61fb1f0a2d073c69d2f5e9befd2c7fa2b04d1594efe9cd1 runtime-v2/runs/final_v2_fast/eval/raw_tools.jsonl
771af56bd6e7f91dd9a20ba6d271f07846c0eccdac0d4ffe0cb82991c4d0a1ba runtime-v2/runs/final_v2_fast/eval/raw_vqa.jsonl
92df69d5c58818a00d2071d14dad8f0155789297b7582de15a583dd4a98c4a71 runtime-v2/runs/final_v2_fast/eval/summary.json
1bf1c5ca785fce32bf0a7248f91e070e7b4c9588369e863d2438bf4d7c788276 runtime-v2/runs/final_v2_fast/eval_compare.txt
e6c066419165ce26f5599e0efc5a41d4fc0b1f59bb862c15cf763a4f3ba3a0ea runtime-v2/runs/final_v2_fast/gpu_after.txt
f3da2a51469f7551f24bfe0833be0567b0374f5ce8caa0d9631fe0327d00221f runtime-v2/runs/final_v2_fast/gpu_before.txt
630d186e382f56a9d42a8f4cb3a5f2ff923f77a3876b58a72e99c44befc45631 runtime-v2/runs/final_v2_fast/greedy.json
37eda03a85270d0c0629ee54c4965e003c06536063f4100a44baff3c31da965e runtime-v2/runs/final_v2_fast/greedy_diff.txt
6eb0bb17cf5b6b0e8a652ef7fb6d31a11485b1074182ce6752a970494de9acf1 runtime-v2/runs/final_v2_fast/mem.txt
ec82b03916c6d8b88c47bb041136182d4139fd82b759b3190e680b0ec4bf5082 runtime-v2/runs/final_v2_fast/perf_matched.json
efc50e8834d005b2eb1b7fb1d0179987eea4f1381c12bdcc932fef96d01d5f09 runtime-v2/runs/final_v2_fast/perf_matched.log
3c5bf2f1dd670eb8dc3a48edd12e0a8685543541a146d25600dbd9c6f572c999 runtime-v2/runs/final_v2_fast/screen_code.json
8f591e3b6c57b106db8e9fb4df8a99a54fcf3184ac68aebfb9f953e9dfc7891a runtime-v2/runs/final_v2_fast/screen_doc.json
0e35cc376c50fd8efe4dedff41a05c94e2619c0cee896250fed3bd0506555e50 runtime-v2/runs/final_v2_fast/startup.txt
ea4b7427752378606219e1cf9357ba40aa67dd33235c12301d500c16a997a71b runtime-v2/runs/hiconc_full_mtp_code.json
0a9ba9984b6cbb131ab25fd6d8f8af8057141dbafcefe4d7f4b762943968a125 runtime-v2/runs/hiconc_full_mtp_synthetic.json
6b93bc4ddd725b554bd3a4967135a8c099a5ad977362b553a780a724d1fbf896 runtime-v2/runs/hiconc_full_nomtp_code.json
8a719835ac522fb33336a5e88a274165bd08ebb9fecf2c668fe699e8358139ec runtime-v2/runs/hiconc_full_nomtp_synthetic.json
66b3ffa838ab282f36ad13cae239e8b4f964ccfdbcc68e08ce706404bc8b01d0 runtime-v2/runs/screen_exact_nomtp_code.json
7c42a88aff1c10777774242f8361cc06382c366d23e3e8e9e300952037b2e2ee runtime-v2/runs/screen_exact_nomtp_synthetic.json
1fb4c028f4786cac1dbf522a38a02a32855539b4dae5bf91add73b9d56722f89 runtime-v2/runs/screen_exact_tm32k_code.json
d608a24eaec0b3124b9c0df90e8fb24a4cf62a3d04f931408f710ef954b0cf31 runtime-v2/runs/screen_exact_tm32k_synthetic.json
1937cc250984d9af1c34fc22b5ca39158d8701eaec2cd78d1cd3b573db8287c8 runtime-v2/runs/screen_exact_tm64k_code.json
d0aaaa27413ca37e111e647db68196948b3278af2f7153058851c168d691dbe3 runtime-v2/runs/screen_exact_tm64k_cutlass_code.json
6f6feb4492963164dbc7dad10f086b96d70cbf68adb83fd27662459de492c422 runtime-v2/runs/screen_exact_tm64k_cutlass_synthetic.json
064eeb61e42a384264749e2902bf0e7c255c6614c158f2c917e70f37f9dafe23 runtime-v2/runs/screen_exact_tm64k_marlin_code.json
c0073c475b7cbd4a6182cecd30cffe17a56ddb98918b559a3d7a5a26453ce437 runtime-v2/runs/screen_exact_tm64k_marlin_synthetic.json
0ad793cdb2cf70fd030c5968f0816772e86d0f0a780064b9b1632f2aff7850e3 runtime-v2/runs/screen_exact_tm64k_s2_code.json
14d4d07b9a95d40f609b487921077ccef2bf57b2f9d25f3c5e020c3ae9fd2676 runtime-v2/runs/screen_exact_tm64k_s2_synthetic.json
5d709710bb44b230b6ee08cf6a562ea45981949935df624b215ac17d4db5cd3b runtime-v2/runs/screen_exact_tm64k_s4_code.json
23c561017cbcff5f3a2730da4992f3f65910026ed310d1947f689e0292163c0b runtime-v2/runs/screen_exact_tm64k_s4_synthetic.json
e1b1fb5cc625e5aa44742c12982bef45e194ec3b59394f7ed110732fc470f2c9 runtime-v2/runs/screen_exact_tm64k_s5_code.json
cdc7bbf511211f8b688d6abcb8278ae7ee45b38d9246c16dae205cacf9b43fdf runtime-v2/runs/screen_exact_tm64k_s5_synthetic.json
da53ac443d172f43721562867a1ccacc8775bf785dbd787816c7d5fd918aaf21 runtime-v2/runs/screen_exact_tm64k_synthetic.json
42f790ca23bf3707695de96fdb2edc8ef31099433ed74073d847cc2c2c41db2c runtime-v2/runs/screen_exactfused_code.json
df8cc82b05501ccc78770b178ef3fcbb5a2c5e2b24d8aed72c0c732737a66a4e runtime-v2/runs/screen_exactfused_synthetic.json
68bff4c8a1d0c80151d734141d8e933c1e8ec64041cb00dca1357741fd8f6921 runtime-v2/runs/screen_frozen_code.json
1ef02dcabdc8052687a7f10093589d3489791af6fdd7db57a61bed59de2640db runtime-v2/runs/screen_frozen_synthetic.json
c30ea79feba85166f0907f328e89173db73d859ba309a008ec48e7f3ebf800e3 runtime-v2/runs/screen_full_tm64k_code.json
3759cbc1e65b4281836a19cfd9bd1ec2d885e6af3dd1d522b97257bfdb75acfb runtime-v2/runs/screen_full_tm64k_synthetic.json
fdebbccb4ccb10b29f43a3339671ac155f756afd6d27a8765c04ceb3f8320567 runtime-v2/runs/screen_fused_code.json
3744bf31104e186420a0103a2aab4578a066d6ae189f75a745038a1e64b7bd2a runtime-v2/runs/screen_fused_synthetic.json
b2a551e06fbe60688f584d30d3c0155a9c362e0d94f677bc381a09df9868f43b runtime-v2/runs/screen_tm32k_code.json
a9cb5f518f107ebae9e68aef34ef4859432f5d3df28e056b21010a7c2080182a runtime-v2/runs/screen_tm32k_synthetic.json
0e4fed3fa486fa7785aff17c0d1bfffa2ff32a6995a48e12a8f81fa197bc8168 runtime-v2/runs/test_mhc_fused.log
73341e398b509936823aeed0a988bf4979cadddc86dcf835967722741dbc68e0 runtime-v2/runs/var/frozen_mmlu_1.log
fb767a933a78863687942d4d229c8a83db618402a788da3451fec189f1d2ea9f runtime-v2/runs/var/frozen_mmlu_1/raw_mmlu_pro.jsonl
96cc5e3107540e10a06de960a373db2a36c7197823da58487ff35d54daca4695 runtime-v2/runs/var/frozen_mmlu_1/summary.json
882f35e5ea9cbdf01c9e384a51b0a73cbbd080093dfea7b09d5521bcaff6935f runtime-v2/runs/var/frozen_mmlu_2.log
cea910838afd0172f8c3996d936bda06d211ac390bf2955a5b67834dcb363b0c runtime-v2/runs/var/frozen_mmlu_2/raw_mmlu_pro.jsonl
3ad1cd1d31662f10549a4896e9f95ce5cced9df1aaabc584b932024fe4f180f4 runtime-v2/runs/var/frozen_mmlu_2/summary.json
6eeac27f8871fcdebccdfeb68b967dd426471b000d386b2d91fd9e8bd9157f0d runtime-v2/runs/var/v2_fast_mmlu_1.log
e32b230c458f1f34167320e18a82c9f67d71f9be5595baf8fe329dc493dff65d runtime-v2/runs/var/v2_fast_mmlu_1/raw_mmlu_pro.jsonl
a123b42dd5e412d7b6ba769ed28f6baabc5d5e6eb991feb6701e61b3b2756c54 runtime-v2/runs/var/v2_fast_mmlu_1/summary.json
ea40811ae5e7b86d215368593563b73043e9c81796a57a37df01801b5402e561 runtime-v2/runs/var/v2_fast_mmlu_2.log
b9f451c6035eaafde49e67513e321c7b97301c019fc0e59a1053c08e2c46e67d runtime-v2/runs/var/v2_fast_mmlu_2/raw_mmlu_pro.jsonl
fd36f9094ea1f847fe0577c05954c4400d93720dba30011eb03ea36a7bf455da runtime-v2/runs/var/v2_fast_mmlu_2/summary.json
333515ef56dddab835aaf72d7d3e41e69acd13feddd29b3eea1a796cdba2c8cf runtime-v2/serve_sglang.sh
608f51ea2fc61860cd74e414c506310abd5bc196b6e98c36a34b58d6c61d08b3 runtime-v2/tests/greedy_outputs.py
f70ffa501857fc0957c3ffbcf6a4143bea059dcf4a02cf7ba568adf5fe45e2ec runtime-v2/tests/test_mhc_fused.py
0e4fed3fa486fa7785aff17c0d1bfffa2ff32a6995a48e12a8f81fa197bc8168 runtime-v2/tests/test_mhc_fused.result.txt
68ea210548cadb0adcc84c9c312bb22b6a4713656ee302c3b0d08f4d18dc1aef runtime-v2/tokenmap/build_token_map.py
3f15c5ab3623692cd2ac59a3fa4bd10cf41bfa6f36049b3a182bb82be99af31e runtime-v2/tokenmap/hot_32k.pt
119fa796636a94aa5bc9b3cc31e0410d34d4a6f4e023b9ee8ed783320c916a57 runtime-v2/tokenmap/hot_64k.pt
e12571bb950e842d6ee21782ca5f15bc7b2375461800744db589c163bb5fec08 runtime-v2/tokenmap/token_map_stats.json
1b95e589cd65a97a97fae93cdeec07fcadbf0ff204be746fe20db32550a2c248 runtime/COMPAT_NOTES.md
e00d2fafe780fcf4c04ab52b040e43ec7143c7bd6e070637563f2724b59888d1 runtime/overlay/python/sglang/srt/configs/__init__.py
bdc7fa2055b799ce07441a5d499fafa554b7b797d4c4a24fd251b846b51260fd runtime/overlay/python/sglang/srt/configs/model_config.py
eb6df8f37ac06e6f439dd24f687e5bf1078599ade28acaa20d8799bf77c7e057 runtime/overlay/python/sglang/srt/configs/sensenova_loop.py
b3b4959f2336d1afdf4f0353a0a0eecfc38495226912022dd862489cbb532c98 runtime/overlay/python/sglang/srt/layers/rotary_embedding/mrope_rope_index.py
0883bffeff0519db0fb8035b3260eca57c48ebe00e42323fb75cb7f455c1ddad runtime/overlay/python/sglang/srt/models/sensenova_loop.py
7fc07bd18b974aa8f54013f2bb39536a65d32ad0cc1a1df2d239ead0dc136754 runtime/overlay/python/sglang/srt/multimodal/processors/qwen_vl.py
68e1076237ed67adfa06530139d79df0783a2519620443a58cce94c5143d56c4 runtime/overlay/python/sglang/srt/utils/hf_transformers/common.py
d93e6342f9487567a7847443eb47b41701b4510474cd5664c8dc51b37eb6f6fd runtime/patches/model_config_mtp_draft.patch
029fa25bb4ea5a16c9fce8de412e7ea6481fc540508c63bdd629026b9a56f926 runtime/patches/sensenova_loop_quant.patch
7b9fd04a5e756a982cac292d314ef2ca84dca0517a4abb4f8a4c009745fd0267 runtime/probe.py
be2e56aca0bdbc48bab616db27b37ab36a170b2a3a35534e8be25b291508e54a runtime/serve_sglang.sh
06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 tokenizer.json
792fa3f0cb88b111e54ef3134c873531008c4df471d108da17903426e308aa7b tokenizer_config.json
bd96830cce1312679aa1f2ea43ed17da20e8ebbcea2398cfa64e2d275a96fdd7 video_preprocessor_config.json