HappyZ happyz
happyz synced commits to refs/pull/7582/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:55 -07:00
347ff8541f Merge 243b5efe0586c1e6fff749fbb52981e01d557bc7 into 55d62262a9
55d62262a9 metal : remove invalid asserts (#7617)
975ec63ff2 metal : add missing asserts (#7617)
fb76ec31a9 ggml : fix YARN + add tests + add asserts (#7617)
Compare 4 commits »
happyz synced commits to refs/pull/7581/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:55 -07:00
eb57fee51f gguf-py : Add tokenizer.ggml.pre to gguf-new-metadata.py (#7627)
55d62262a9 metal : remove invalid asserts (#7617)
975ec63ff2 metal : add missing asserts (#7617)
fb76ec31a9 ggml : fix YARN + add tests + add asserts (#7617)
Compare 5 commits »
happyz synced commits to refs/pull/7587/head at happyz/llama.cpp from mirror 2024-05-29 18:19:55 -07:00
8a8f8b953f llama : print a log of the total cache size
1494a1841e llama : throw on unknown tokenizer types
21ccd645df llama : use vectors and avoid has_cache
9964cd02f7 llama : cache llama_token_to_piece
fb76ec31a9 ggml : fix YARN + add tests + add asserts (#7617)
Compare 21 commits »
happyz synced commits to refs/pull/7587/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:55 -07:00
eb57fee51f gguf-py : Add tokenizer.ggml.pre to gguf-new-metadata.py (#7627)
55d62262a9 metal : remove invalid asserts (#7617)
8a8f8b953f llama : print a log of the total cache size
1494a1841e llama : throw on unknown tokenizer types
Compare 19 commits »
happyz synced commits to refs/pull/7568/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:55 -07:00
fc83fb0d72 Merge 4f64f7ebb018994b9e29ea7fabffbcbdda20a420 into eb57fee51f
eb57fee51f gguf-py : Add tokenizer.ggml.pre to gguf-new-metadata.py (#7627)
55d62262a9 metal : remove invalid asserts (#7617)
975ec63ff2 metal : add missing asserts (#7617)
fb76ec31a9 ggml : fix YARN + add tests + add asserts (#7617)
Compare 5 commits »
happyz synced commits to refs/pull/7548/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:54 -07:00
bf8e973163 Merge 347fb56d57a19df05fe6d3129aeede2ecf662229 into eb57fee51f
347fb56d57 SimpleChat: Save message internally in handle_response itself
eb57fee51f gguf-py : Add tokenizer.ggml.pre to gguf-new-metadata.py (#7627)
fbc8c8279f SimpleChat:theResp-origMsg: Undo a prev change to fix non trim
c039a7311c SimpleChat:WIP:Collate internally, Stream mode Trap exceptions
Compare 19 commits »
happyz synced commits to refs/pull/7555/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:54 -07:00
55d62262a9 metal : remove invalid asserts (#7617)
975ec63ff2 metal : add missing asserts (#7617)
fb76ec31a9 ggml : fix YARN + add tests + add asserts (#7617)
cce3dcffc5 cuda : non-cont concat support (#7610)
Compare 10 commits »
happyz synced commits to refs/pull/7553/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:54 -07:00
eb57fee51f gguf-py : Add tokenizer.ggml.pre to gguf-new-metadata.py (#7627)
55d62262a9 metal : remove invalid asserts (#7617)
975ec63ff2 metal : add missing asserts (#7617)
fb76ec31a9 ggml : fix YARN + add tests + add asserts (#7617)
Compare 5 commits »
happyz synced commits to refs/pull/7551/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:54 -07:00
eb57fee51f gguf-py : Add tokenizer.ggml.pre to gguf-new-metadata.py (#7627)
55d62262a9 metal : remove invalid asserts (#7617)
975ec63ff2 metal : add missing asserts (#7617)
fb76ec31a9 ggml : fix YARN + add tests + add asserts (#7617)
Compare 5 commits »
happyz synced commits to refs/pull/7548/head at happyz/llama.cpp from mirror 2024-05-29 18:19:53 -07:00
347fb56d57 SimpleChat: Save message internally in handle_response itself
fbc8c8279f SimpleChat:theResp-origMsg: Undo a prev change to fix non trim
c039a7311c SimpleChat:WIP:Collate internally, Stream mode Trap exceptions
122479bcaf Readme: Add a entry for simplechat in the http server section
0eb9d3ecbe SimpleChat: readme stream-utf-8 trim-english deps, exception2error
Compare 14 commits »
happyz synced commits to refs/pull/7537/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:53 -07:00
37eaaa9451 Merge 80787c2a26c54998fff5f621e5aa7ae9866d0bfd into 55d62262a9
55d62262a9 metal : remove invalid asserts (#7617)
975ec63ff2 metal : add missing asserts (#7617)
fb76ec31a9 ggml : fix YARN + add tests + add asserts (#7617)
Compare 4 commits »
happyz synced commits to refs/pull/7535/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:53 -07:00
55d62262a9 metal : remove invalid asserts (#7617)
975ec63ff2 metal : add missing asserts (#7617)
fb76ec31a9 ggml : fix YARN + add tests + add asserts (#7617)
cce3dcffc5 cuda : non-cont concat support (#7610)
Compare 10 commits »
happyz synced commits to refs/pull/7530/head at happyz/llama.cpp from mirror 2024-05-29 18:19:53 -07:00
fef99155cc Build vocab.special_tokens_cache using vocab token types
happyz synced commits to refs/pull/7514/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:52 -07:00
eb57fee51f gguf-py : Add tokenizer.ggml.pre to gguf-new-metadata.py (#7627)
55d62262a9 metal : remove invalid asserts (#7617)
975ec63ff2 metal : add missing asserts (#7617)
fb76ec31a9 ggml : fix YARN + add tests + add asserts (#7617)
Compare 13 commits »
happyz synced commits to refs/pull/7527/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:52 -07:00
eb57fee51f gguf-py : Add tokenizer.ggml.pre to gguf-new-metadata.py (#7627)
cc7aef6829 fix AMD
55d62262a9 metal : remove invalid asserts (#7617)
62056fa679 add autogenerated .cu files
Compare 11 commits »
happyz synced commits to refs/pull/7527/head at happyz/llama.cpp from mirror 2024-05-29 18:19:52 -07:00
cc7aef6829 fix AMD
62056fa679 add autogenerated .cu files
2eb0f7f7e8 make generate_cu_files.py executable
9740ae0adc fix cmake
af95ae49a3 fix metal tests
Compare 6 commits »
happyz synced commits to refs/pull/7522/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:52 -07:00
eb57fee51f gguf-py : Add tokenizer.ggml.pre to gguf-new-metadata.py (#7627)
55d62262a9 metal : remove invalid asserts (#7617)
975ec63ff2 metal : add missing asserts (#7617)
fb76ec31a9 ggml : fix YARN + add tests + add asserts (#7617)
Compare 5 commits »
happyz synced commits to refs/pull/7504/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:52 -07:00
55d62262a9 metal : remove invalid asserts (#7617)
975ec63ff2 metal : add missing asserts (#7617)
fb76ec31a9 ggml : fix YARN + add tests + add asserts (#7617)
cce3dcffc5 cuda : non-cont concat support (#7610)
Compare 11 commits »
happyz synced commits to refs/pull/7487/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:51 -07:00
55d62262a9 metal : remove invalid asserts (#7617)
975ec63ff2 metal : add missing asserts (#7617)
fb76ec31a9 ggml : fix YARN + add tests + add asserts (#7617)
cce3dcffc5 cuda : non-cont concat support (#7610)
Compare 5 commits »
happyz synced commits to refs/pull/7499/merge at happyz/llama.cpp from mirror 2024-05-29 18:19:51 -07:00
2e39d0e32e Merge 550a97bfe8e14730e045a31bbbd5d996edd447b9 into 55d62262a9
55d62262a9 metal : remove invalid asserts (#7617)
975ec63ff2 metal : add missing asserts (#7617)
fb76ec31a9 ggml : fix YARN + add tests + add asserts (#7617)
Compare 4 commits »