Default Branch

aa79524c51 · HIP: remove the use of __HIP_PLATFORM_AMD__, explicitly support only AMD targets (#14945) · Updated 2025-07-30 02:23:04 +08:00

Branches

b98f80a6b4 · server : test alternative LRU logic · Updated 2025-07-30 02:19:21 +08:00

1
1

0591b39e48 · ops: add MUSA · Updated 2025-07-29 17:25:32 +08:00

7
1

381879e0ac · cont : tmp · Updated 2025-07-29 12:42:55 +08:00

31
3

fb371c18ec · bench,common : add CPU extra buffer types · Updated 2025-07-29 02:53:18 +08:00

8
1

e9f7e7cce2 · ops : update BLAS · Updated 2025-07-28 14:42:57 +08:00

18
1

e2661edd24 · ggml : repack block_iq4_nlx8 · Updated 2025-07-27 23:53:03 +08:00

31
1

fd8be28959 · vulkan: Add Integer Dot Product mul_mat_vec shader for legacy quants · Updated 2025-07-27 23:21:39 +08:00

24
1

ee9daba3b2 · vulkan: add ops docs · Updated 2025-07-27 21:31:02 +08:00

23
1

dbf7d782d4 · vulkan: fix debug mode issues · Updated 2025-07-26 18:25:42 +08:00

32
1

a5801f408f · sync : ggml · Updated 2025-07-25 19:31:39 +08:00

37
2

6f4c57236b · server : fix vision test regex · Updated 2025-07-25 16:22:36 +08:00

59
1

aa5a7c6d6d · profiler: output all tensor names · Updated 2025-07-25 10:14:41 +08:00

42
2

e65aa69402 · context : only sort outputs when needed · Updated 2025-07-24 23:06:34 +08:00

46
1

a124399f19 · sched : fix multiple evaluations of the same graph with pipeline parallelism · Updated 2025-07-24 22:03:14 +08:00

46
1

978c88ba0a · cont : add TODO · Updated 2025-07-24 21:31:10 +08:00

48
2

1ef3cc1a87 · imatrix : use GGUF regardless of the output filename · Updated 2025-07-24 11:22:41 +08:00

53
2

7b660a917f · graph : comment the s_copy views · Updated 2025-07-24 09:48:24 +08:00

63
2

dfcff338af · tests: Fix OPT_STEP_SGD test-backend-ops · Updated 2025-07-23 15:41:37 +08:00

63
3

55cf48de1e · cuda : fix multi-seq, quantized FA · Updated 2025-07-23 01:48:53 +08:00

95
2

de12f8ac50 · convert : begin handling pre-quantized models · Updated 2025-07-22 16:11:34 +08:00

80
1