Default Branch

main ec72b44417 · Add quantize/dequantize for mxfp8 and nvfp4 (#2688) · Updated 2025-10-29 07:23:12 +08:00

ZIP  TAR.GZ

Branches

cpp20 4515866024 · Change the linux test to ubuntu 24.04 · Updated 2025-01-21 14:58:05 +08:00    zhangyiss	539 9		ZIP  TAR.GZ
winograd_qupdate f14b4d72de · Remove unnecessary copy from winograd · Updated 2025-01-07 06:06:03 +08:00    zhangyiss	526 1		ZIP  TAR.GZ
packed-quants c02e14c264 · Add the 3bit packed qmm_t · Updated 2024-12-18 14:16:30 +08:00    zhangyiss	562 19		ZIP  TAR.GZ
dynamic_reshape 0c1155faf5 · binding + tests · Updated 2024-12-10 04:57:36 +08:00    zhangyiss	580 3		ZIP  TAR.GZ
q-sdpa 82a956c1d9 · fix test · Updated 2024-12-07 02:26:54 +08:00    zhangyiss	599 5		ZIP  TAR.GZ
gs16 890fdd1ef0 · start · Updated 2024-12-04 11:53:18 +08:00    zhangyiss	600 1		ZIP  TAR.GZ
gemm-tuner e21143961c · Add init python binding for tunable matmul · Updated 2024-12-04 05:09:34 +08:00    zhangyiss	600 3		ZIP  TAR.GZ
mat-attn 716277d246 · Enable attn build outside of jit · Updated 2024-11-23 02:12:20 +08:00    zhangyiss	615 17		ZIP  TAR.GZ
socket-distributed-layers-gloo 87b680766e · Gloo backend support · Updated 2024-11-14 05:52:37 +08:00    zhangyiss	643 14		ZIP  TAR.GZ
alternative_fence fc6494cac7 · register in task submission · Updated 2024-11-06 06:42:51 +08:00    zhangyiss	645 1		ZIP  TAR.GZ
socket-distributed-layers d82699f0f1 · Merge branch 'distributed-layers' into socket-distributed-layers · Updated 2024-11-06 03:36:16 +08:00    zhangyiss	643 12		ZIP  TAR.GZ
sockets-distributed 6fc00d2c10 · Add rudimentary barrier · Updated 2024-11-06 03:34:55 +08:00    zhangyiss	643 7		ZIP  TAR.GZ
quantized-kv-update f5b0f11968 · add fast::quantized_kv_update · Updated 2024-10-26 15:24:49 +08:00    zhangyiss	667 7		ZIP  TAR.GZ
raw-sockets-distributed 3fe98bacc7 · Raw sockets · Updated 2024-09-09 15:38:15 +08:00    zhangyiss	741 6		ZIP  TAR.GZ
ab-nf4-quant 152092957c · Add NF4 quant · Updated 2024-06-28 04:16:31 +08:00    zhangyiss	837 1		ZIP  TAR.GZ
async_all_reduce 3a1df968cf · Add async all reduce and donation · Updated 2024-05-30 13:54:32 +08:00    zhangyiss	871 1		ZIP  TAR.GZ
io-dev 8242d6d5ef · Add locks to FileStream · Updated 2024-05-09 14:19:27 +08:00    zhangyiss	917 5		ZIP  TAR.GZ
checkpoint_module 0dbe80a024 · try again with checkpointed classes · Updated 2024-03-07 02:38:04 +08:00    zhangyiss	1060 4		ZIP  TAR.GZ
compile-test f5ece1d98d · Tmp · Updated 2024-01-23 10:38:11 +08:00    zhangyiss	1197 23		ZIP  TAR.GZ
priority-queue-eval 5b46b9bc52 · Add priority-queue eval · Updated 2024-01-14 11:58:20 +08:00    zhangyiss	1227 3		ZIP  TAR.GZ