HappyZ happyz
happyz synced commits to refs/pull/6664/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:15 -07:00
04fbc5f23e Add Command R chat template (#6650)
f184dd9208 flake.lock: Update (#6669)
422c2aff1c Added support for GGML_OP_CLAMP in Metal (#6662)
8800226d65 Fix --split-max-size (#6655)
Compare 8 commits »
happyz synced commits to refs/pull/6661/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:15 -07:00
04fbc5f23e Add Command R chat template (#6650)
f184dd9208 flake.lock: Update (#6669)
422c2aff1c Added support for GGML_OP_CLAMP in Metal (#6662)
8800226d65 Fix --split-max-size (#6655)
Compare 8 commits »
happyz synced commits to refs/pull/6659/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:14 -07:00
04fbc5f23e Add Command R chat template (#6650)
f184dd9208 flake.lock: Update (#6669)
422c2aff1c Added support for GGML_OP_CLAMP in Metal (#6662)
8800226d65 Fix --split-max-size (#6655)
Compare 8 commits »
happyz synced commits to refs/pull/6658/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:14 -07:00
04fbc5f23e Add Command R chat template (#6650)
f184dd9208 flake.lock: Update (#6669)
422c2aff1c Added support for GGML_OP_CLAMP in Metal (#6662)
8800226d65 Fix --split-max-size (#6655)
Compare 8 commits »
happyz synced commits to refs/pull/6655/head at happyz/llama.cpp from mirror 2024-04-14 11:13:14 -07:00
650db0f25f add --split-max-size to readme
708a0b0516 explicitly define which scripts to run
e53bc29c25 clean up before and after test
Compare 3 commits »
happyz synced commits to refs/pull/6648/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:14 -07:00
04fbc5f23e Add Command R chat template (#6650)
f184dd9208 flake.lock: Update (#6669)
422c2aff1c Added support for GGML_OP_CLAMP in Metal (#6662)
8800226d65 Fix --split-max-size (#6655)
Compare 8 commits »
happyz synced commits to refs/pull/6644/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:14 -07:00
ee87802300 Merge 1b988855dca2ced3850dbe40812707e639b1dbd6 into 04fbc5f23e
04fbc5f23e Add Command R chat template (#6650)
f184dd9208 flake.lock: Update (#6669)
422c2aff1c Added support for GGML_OP_CLAMP in Metal (#6662)
8800226d65 Fix --split-max-size (#6655)
Compare 8 commits »
happyz synced commits to refs/pull/6640/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:13 -07:00
04fbc5f23e Add Command R chat template (#6650)
f184dd9208 flake.lock: Update (#6669)
422c2aff1c Added support for GGML_OP_CLAMP in Metal (#6662)
8800226d65 Fix --split-max-size (#6655)
Compare 9 commits »
happyz synced commits to refs/pull/6638/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:13 -07:00
f184dd9208 flake.lock: Update (#6669)
422c2aff1c Added support for GGML_OP_CLAMP in Metal (#6662)
8800226d65 Fix --split-max-size (#6655)
e689fc4e91 [bug fix] convert github repository_owner to lowercase (#6673)
Compare 8 commits »
happyz synced commits to refs/pull/6635/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:13 -07:00
04fbc5f23e Add Command R chat template (#6650)
f184dd9208 flake.lock: Update (#6669)
422c2aff1c Added support for GGML_OP_CLAMP in Metal (#6662)
8800226d65 Fix --split-max-size (#6655)
Compare 23 commits »
happyz synced commits to refs/pull/6635/head at happyz/llama.cpp from mirror 2024-04-14 11:13:13 -07:00
e3f73604d5 Move QK norm stack to private function so it's easier to read
f7b40d7650 Revert formatter
0dc779bff9 Removed warnings
8dcd9978d2 Fix accidental removal
0ec53cfff7 Converge StableLM and StableLM2 code to simplify graph construction
Compare 20 commits »
happyz synced commits to refs/pull/6622/head at happyz/llama.cpp from mirror 2024-04-14 11:13:12 -07:00
9db2000849 revert to malloc/free solution, for threaad safe
happyz synced commits to refs/pull/6602/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:12 -07:00
04fbc5f23e Add Command R chat template (#6650)
f184dd9208 flake.lock: Update (#6669)
422c2aff1c Added support for GGML_OP_CLAMP in Metal (#6662)
8800226d65 Fix --split-max-size (#6655)
Compare 8 commits »
happyz synced commits to refs/pull/6590/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:12 -07:00
de17e3f745 fix memcpy() crash, add missed cmd in guide, fix softmax (#6622)
b5e7285baf CUDA: fix matrix multiplication logic for tests (#6667)
Compare 3 commits »
happyz synced commits to refs/pull/6588/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:12 -07:00
04fbc5f23e Add Command R chat template (#6650)
f184dd9208 flake.lock: Update (#6669)
422c2aff1c Added support for GGML_OP_CLAMP in Metal (#6662)
8800226d65 Fix --split-max-size (#6655)
Compare 9 commits »
happyz synced commits to refs/pull/6578/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:12 -07:00
a4ec34e1cd convert : enable the `--use-temp-file` cli flag (#6645)
de17e3f745 fix memcpy() crash, add missed cmd in guide, fix softmax (#6622)
b5e7285baf CUDA: fix matrix multiplication logic for tests (#6667)
Compare 4 commits »
happyz synced commits to refs/pull/6563/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:12 -07:00
f2af1fa448 Merge 9acb43d7fa0b8da867570c975d33f0728951ca46 into 04fbc5f23e
04fbc5f23e Add Command R chat template (#6650)
f184dd9208 flake.lock: Update (#6669)
422c2aff1c Added support for GGML_OP_CLAMP in Metal (#6662)
8800226d65 Fix --split-max-size (#6655)
Compare 9 commits »
happyz synced commits to refs/pull/6522/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:11 -07:00
fcc09e8ce2 Merge a37d88568336ec949865e166eaf1454841f4cdb5 into f184dd9208
f184dd9208 flake.lock: Update (#6669)
422c2aff1c Added support for GGML_OP_CLAMP in Metal (#6662)
8800226d65 Fix --split-max-size (#6655)
e689fc4e91 [bug fix] convert github repository_owner to lowercase (#6673)
Compare 7 commits »
happyz synced commits to refs/pull/6511/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:11 -07:00
1b02fbf3bf Merge b9c984b2a463fdca12b92d9be2c7639b8ff7852f into de17e3f745
de17e3f745 fix memcpy() crash, add missed cmd in guide, fix softmax (#6622)
b5e7285baf CUDA: fix matrix multiplication logic for tests (#6667)
Compare 3 commits »
happyz synced commits to refs/pull/6502/merge at happyz/llama.cpp from mirror 2024-04-14 11:13:11 -07:00
04fbc5f23e Add Command R chat template (#6650)
f184dd9208 flake.lock: Update (#6669)
422c2aff1c Added support for GGML_OP_CLAMP in Metal (#6662)
8800226d65 Fix --split-max-size (#6655)
Compare 9 commits »