happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
8,297 Commits 543 Branches 5,640 Tags 1.5 GiB
Commit Graph

44 Commits

Author SHA1 Message Date
Yu, Zijun 5525bac078 Use bias instead of zp in test-backend-ops 2026-02-13 17:38:21 +08:00
Yu, Zijun 2a6a95eb77 Fix MUL_MAT with broadcast; Add unsupported MUL_MAT FLASH_ATTN cases 2026-02-13 15:36:51 +08:00
Yu, Zijun 1a54965c43 Suppress logging and add error handling to allow test-backend-ops to complete 2026-02-13 10:43:52 +08:00
Yu, Zijun d5d673cde3 Fix test-backend-ops crash glu, get_rows, scale, rms_norm, add 2026-02-12 17:32:19 +08:00
Yu, Zijun 900dd76c24 Refactor weight tensor processing 2026-02-11 10:15:09 +08:00
Yu, Zijun 0ee7e05485 Extract zp directly instead of bias 2026-02-11 10:15:09 +08:00
Yu, Zijun b6c0697d10 Avoid re-compilation in llama-bench 2026-02-11 10:15:09 +08:00
Yu, Zijun 18ab0f562b Remove hardcode names 2026-02-11 10:15:09 +08:00
Yu, Zijun c840210213 Don't put kvcache on GPU in stateful mode 2026-02-11 10:15:09 +08:00
Yu, Zijun 1c0a47a485 Fix --direct-io 0 2026-02-11 10:15:09 +08:00
Yu, Zijun 9a15c8b0cf Change ov backend buffer is_host to false 2026-01-21 15:23:12 +08:00
Yu, Zijun cfc471353d FIX: use remote tensor from singleton 2026-01-15 11:39:08 -08:00
Yu, Zijun a356b44477 only use remote tensor for kvcache for GPU 2026-01-15 11:39:08 -08:00
Yu, Zijun 88d1d17eac only use remote tensor for kvcache 2026-01-15 11:39:08 -08:00
Yu, Zijun 8273a7c2f4 Use ggml_aligned_malloc 2026-01-15 11:39:08 -08:00
Yu, Zijun d757849741 Put kvcache on GPU 2026-01-15 11:39:08 -08:00
Yu, Zijun 3fdcb6ab72 Add ov_backend_host_buffer; Use cached remote context 2026-01-15 11:39:08 -08:00
Yu, Zijun 72bba828df Use shared_buffer for GPU NPU; Refactor 2026-01-15 11:39:08 -08:00
Yu, Zijun 22d9c17a6f backend buffer: allocate on host 2026-01-15 11:39:08 -08:00
Yu, Zijun 2a9d4ca836 Refactor: split ov_graph_compute for dynamic and static 2026-01-15 11:39:08 -08:00
Yu, Zijun 072dde0b2b change graph to 4d, support multi sequences 2026-01-15 11:28:48 -08:00
Yu, Zijun 303923aba7 Clean placeholders in ggml-openvino.cpp 2026-01-15 11:27:30 -08:00
Yu, Zijun eba8113dc4 Style: middle ptr and ref align, omit optional struct keyword 2026-01-15 11:27:30 -08:00
Yu, Zijun bd3093f90c Style: use switch in supports_ops 2026-01-15 11:27:30 -08:00
Yu, Zijun 299f4923bb fix after rebasing 2026-01-15 11:26:00 -08:00
Yu, Zijun e4bfe5a20d Add Q5_K to support phi-3-q4_k_m 2026-01-15 11:26:00 -08:00
Yu, Zijun 1a38339cea Fix ROPE accuracy when freq_scale != 1 2026-01-15 11:26:00 -08:00
Yu, Zijun 597561242f Add GeGLU 2026-01-15 11:20:31 -08:00
Yu, Zijun b593428eb3 Dequantize q4_1 q4_k q6_k for NPU 2026-01-15 11:20:31 -08:00
Yu, Zijun 9ca53c7991 Add NPU Q4_0 support 2026-01-15 11:20:31 -08:00
Yu, Zijun 9900245e0b Fix test-backend-ops: Treat quantized tensors as weights 2026-01-15 11:20:31 -08:00
Yu, Zijun 6ab76ed10a Fix accuracy: disable cpu_repack 2026-01-15 11:19:15 -08:00
Yu, Zijun 3e897df51c Update supports_buft and supports_op for quantized models 2026-01-15 11:19:15 -08:00
Yu, Zijun 56d596775d Change openvino device_type to GPU; Enable flash_attn 2026-01-15 11:19:15 -08:00
Yu, Zijun 65e1b1af6d Fix after rebasing 
- Layout of cache k and cache v are unified: [seq, n_head, head_size]
- Add CPY and FLASH_ATTN_EXT, flash attn is not used yet
- Skip test-backend-ops due to flash attn test crash
- Add mutex around graph conversion to avoid test-thread-safety fali in the future
- Update NPU config
- Update GPU config to disable SDPA opt to make phi-3 run
 2026-01-15 11:19:15 -08:00
Yu, Zijun f4123be967 Fix test-backend-ops 2026-01-15 11:19:15 -08:00
Yu, Zijun 839f8c66a0 Remove CPY 2026-01-15 11:19:15 -08:00
Yu, Zijun 63d000ba40 Support op SET_ROWS 2026-01-15 11:19:15 -08:00
Yu, Zijun fc865340d5 Fix test-backend-ops 2026-01-15 10:26:28 -08:00
Yu, Zijun 75eec6265f Fix llama-bench; Clang-format 2026-01-15 10:26:28 -08:00
Yu, Zijun 44f4cf34b1 Fix Phi3 ROPE; Add test-backend-ops 2026-01-15 10:26:28 -08:00
Yu, Zijun 73ee84fffe Add SwiGLU 2026-01-15 10:20:18 -08:00
Yu, Zijun a0b30529bf FIX: backend buffer type issue 2026-01-15 10:10:00 -08:00
Zijun Yu 4c905b2b25 fix build error 2026-01-15 10:10:00 -08:00
Renamed from ggml/src/ggml-openvino.cpp (Browse further)