HappyZ happyz
0 Followers · 0 Following
Repositories
18
 Projects Packages Public Activity Starred Repositories
happyz synced commits to refs/pull/7797/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:31 -07:00
47681822e6 Merge f03e9b935b into 6fcd1331ef
6fcd1331ef llama : more checks before assuming FIM tokens (#7644)
41b9260f18 convert : add Poro-34B-chat tokenizer support (#7713)
Compare 3 commits »
happyz synced commits to refs/pull/7840/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:31 -07:00
7ce8a69435 Merge 322d611378 into 6fcd1331ef
6fcd1331ef llama : more checks before assuming FIM tokens (#7644)
41b9260f18 convert : add Poro-34B-chat tokenizer support (#7713)
Compare 3 commits »
happyz synced commits to refs/pull/7835/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:31 -07:00
f4bc7ddef0 Merge d9452267a0 into 66ef1ceedf
66ef1ceedf metal : utilize max shared memory for mul_mat_id (#7935)
e65bbf606c llama-bench : fix RPC indication (#7936)
d9452267a0 fix: QWEN2MOE support for expert_feed_forward_length
6fcd1331ef llama : more checks before assuming FIM tokens (#7644)
Compare 6 commits »
happyz synced commits to refs/pull/7835/head at happyz/llama.cpp from mirror 2024-06-14 09:23:31 -07:00
d9452267a0 fix: QWEN2MOE support for expert_feed_forward_length
happyz synced commits to refs/pull/7814/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:31 -07:00
4998095918 Merge 948559260a into 66ef1ceedf
66ef1ceedf metal : utilize max shared memory for mul_mat_id (#7935)
e65bbf606c llama-bench : fix RPC indication (#7936)
6fcd1331ef llama : more checks before assuming FIM tokens (#7644)
41b9260f18 convert : add Poro-34B-chat tokenizer support (#7713)
Compare 5 commits »
happyz synced commits to refs/pull/7790/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:30 -07:00
efc36778ca Merge 488cbfae083d26b45544105a2e588ea9ec7c62be into 6fcd1331ef
6fcd1331ef llama : more checks before assuming FIM tokens (#7644)
41b9260f18 convert : add Poro-34B-chat tokenizer support (#7713)
Compare 3 commits »
happyz synced commits to refs/pull/7713/head at happyz/llama.cpp from mirror 2024-06-14 09:23:30 -07:00
af019105f1 Update llama.cpp
1c03036c15 Update convert-hf-to-gguf-update.py
5d676a2245 Change Poro-34B-chat to poro-chat
cd974f14ad Change Poro-34B-chat to poro-chat
a75f69a63e Update convert-hf-to-gguf-update.py
Compare 5 commits »
happyz synced commits to refs/pull/7710/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:30 -07:00
ea96c90332 Merge c776fb8033 into 66ef1ceedf
66ef1ceedf metal : utilize max shared memory for mul_mat_id (#7935)
e65bbf606c llama-bench : fix RPC indication (#7936)
6fcd1331ef llama : more checks before assuming FIM tokens (#7644)
41b9260f18 convert : add Poro-34B-chat tokenizer support (#7713)
Compare 7 commits »
happyz synced commits to refs/pull/7795/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:30 -07:00
2ed2c7b4e4 Merge 728e1b4da0 into 172c825684
172c825684 rpc : fix ggml_backend_rpc_supports_buft() (#7918)
Compare 2 commits »
happyz synced commits to refs/pull/7751/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:30 -07:00
23d260599c Merge 02eb91213e into 66ef1ceedf
66ef1ceedf metal : utilize max shared memory for mul_mat_id (#7935)
e65bbf606c llama-bench : fix RPC indication (#7936)
6fcd1331ef llama : more checks before assuming FIM tokens (#7644)
41b9260f18 convert : add Poro-34B-chat tokenizer support (#7713)
Compare 5 commits »
happyz synced commits to refs/pull/7705/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:29 -07:00
b757f95207 Merge 5175117a09 into 66ef1ceedf
66ef1ceedf metal : utilize max shared memory for mul_mat_id (#7935)
e65bbf606c llama-bench : fix RPC indication (#7936)
6fcd1331ef llama : more checks before assuming FIM tokens (#7644)
41b9260f18 convert : add Poro-34B-chat tokenizer support (#7713)
Compare 5 commits »
happyz synced commits to refs/pull/7710/head at happyz/llama.cpp from mirror 2024-06-14 09:23:29 -07:00
c776fb8033 remove duplicated extras
996b35a0ad remove useless backend check
Compare 2 commits »
happyz synced commits to refs/pull/7553/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:28 -07:00
16448ae17f Merge 9bed1aebbe into 66ef1ceedf
66ef1ceedf metal : utilize max shared memory for mul_mat_id (#7935)
e65bbf606c llama-bench : fix RPC indication (#7936)
6fcd1331ef llama : more checks before assuming FIM tokens (#7644)
41b9260f18 convert : add Poro-34B-chat tokenizer support (#7713)
Compare 5 commits »
happyz synced commits to refs/pull/7531/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:28 -07:00
2c2a74e151 Merge 33425a7e1e into 66ef1ceedf
66ef1ceedf metal : utilize max shared memory for mul_mat_id (#7935)
e65bbf606c llama-bench : fix RPC indication (#7936)
6fcd1331ef llama : more checks before assuming FIM tokens (#7644)
41b9260f18 convert : add Poro-34B-chat tokenizer support (#7713)
Compare 5 commits »
happyz synced commits to refs/pull/7522/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:28 -07:00
85e1f71570 Merge aa3fd500b1 into 66ef1ceedf
66ef1ceedf metal : utilize max shared memory for mul_mat_id (#7935)
e65bbf606c llama-bench : fix RPC indication (#7936)
6fcd1331ef llama : more checks before assuming FIM tokens (#7644)
41b9260f18 convert : add Poro-34B-chat tokenizer support (#7713)
Compare 7 commits »
happyz synced commits to refs/pull/7648/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:28 -07:00
6904b1fdaf Merge ff0fc6892a into 6fcd1331ef
6fcd1331ef llama : more checks before assuming FIM tokens (#7644)
41b9260f18 convert : add Poro-34B-chat tokenizer support (#7713)
172c825684 rpc : fix ggml_backend_rpc_supports_buft() (#7918)
Compare 4 commits »
happyz synced commits to refs/pull/7514/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:28 -07:00
461e080a30 Merge 6d2464aef5 into 66ef1ceedf
66ef1ceedf metal : utilize max shared memory for mul_mat_id (#7935)
e65bbf606c llama-bench : fix RPC indication (#7936)
6fcd1331ef llama : more checks before assuming FIM tokens (#7644)
41b9260f18 convert : add Poro-34B-chat tokenizer support (#7713)
Compare 5 commits »
happyz synced commits to refs/pull/7497/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:27 -07:00
9705795a90 Merge 46c0cd78ef103d83cbec3d8d0dbd36574f0dd889 into 66ef1ceedf
66ef1ceedf metal : utilize max shared memory for mul_mat_id (#7935)
e65bbf606c llama-bench : fix RPC indication (#7936)
6fcd1331ef llama : more checks before assuming FIM tokens (#7644)
41b9260f18 convert : add Poro-34B-chat tokenizer support (#7713)
Compare 5 commits »
happyz synced commits to refs/pull/6999/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:27 -07:00
e127095558 Merge a096383149cc73d911f157dae718d093da458f08 into 66ef1ceedf
66ef1ceedf metal : utilize max shared memory for mul_mat_id (#7935)
e65bbf606c llama-bench : fix RPC indication (#7936)
6fcd1331ef llama : more checks before assuming FIM tokens (#7644)
41b9260f18 convert : add Poro-34B-chat tokenizer support (#7713)
Compare 5 commits »
happyz synced commits to refs/pull/7239/merge at happyz/llama.cpp from mirror 2024-06-14 09:23:27 -07:00
978579faf9 Merge f4f5b7ac56 into 41b9260f18
41b9260f18 convert : add Poro-34B-chat tokenizer support (#7713)
172c825684 rpc : fix ggml_backend_rpc_supports_buft() (#7918)
a55eb1bf0f readme : Remove outdated instructions from README.md (#7914) [no ci]
f578b86b21 move BLAS to a separate backend (#6210)
Compare 64 commits »